noshot 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (228) hide show
  1. noshot/data/ML TS XAI/ML/1. PCA - EDA/PCA-EDA.ipynb +207 -0
  2. noshot/data/ML TS XAI/ML/1. PCA - EDA/balance-scale.csv +626 -0
  3. noshot/data/ML TS XAI/ML/1. PCA - EDA/input.txt +625 -0
  4. noshot/data/ML TS XAI/ML/2. KNN Classifier/KNN.ipynb +287 -0
  5. noshot/data/ML TS XAI/ML/2. KNN Classifier/balance-scale.csv +626 -0
  6. noshot/data/ML TS XAI/ML/2. KNN Classifier/input.txt +625 -0
  7. noshot/data/ML TS XAI/ML/3. Linear Discriminant Analysis/LDA.ipynb +83 -0
  8. noshot/data/ML TS XAI/ML/3. Linear Discriminant Analysis/balance-scale.csv +626 -0
  9. noshot/data/ML TS XAI/ML/3. Linear Discriminant Analysis/input.txt +625 -0
  10. noshot/data/ML TS XAI/ML/4. Linear Regression/Linear-Regression.ipynb +117 -0
  11. noshot/data/ML TS XAI/ML/4. Linear Regression/machine-data.csv +210 -0
  12. noshot/data/ML TS XAI/ML/5. Logistic Regression/Logistic-Regression.ipynb +137 -0
  13. noshot/data/ML TS XAI/ML/5. Logistic Regression/wine-dataset.csv +179 -0
  14. noshot/data/ML TS XAI/ML/6. Bayesian Classifier/Bayesian.ipynb +129 -0
  15. noshot/data/ML TS XAI/ML/6. Bayesian Classifier/wine-dataset.csv +179 -0
  16. {noshot-0.1.6.dist-info → noshot-0.1.8.dist-info}/METADATA +2 -2
  17. noshot-0.1.8.dist-info/RECORD +24 -0
  18. noshot/data/ML TS XAI/AIDS/1. Implement Basic Search Strategies/(A) Breadth First Search.ipynb +0 -112
  19. noshot/data/ML TS XAI/AIDS/1. Implement Basic Search Strategies/(B) Depth First Search.ipynb +0 -111
  20. noshot/data/ML TS XAI/AIDS/1. Implement Basic Search Strategies/(C) Uniform Cost Search.ipynb +0 -134
  21. noshot/data/ML TS XAI/AIDS/1. Implement Basic Search Strategies/(D) Depth Limites Search.ipynb +0 -115
  22. noshot/data/ML TS XAI/AIDS/1. Implement Basic Search Strategies/(E) Iterative Deepening DFS.ipynb +0 -123
  23. noshot/data/ML TS XAI/AIDS/10. ANOVA/2_ANOVA.csv +0 -769
  24. noshot/data/ML TS XAI/AIDS/10. ANOVA/One Way ANOVA (Repeated Measure).ipynb +0 -126
  25. noshot/data/ML TS XAI/AIDS/10. ANOVA/One Way ANOVA.ipynb +0 -134
  26. noshot/data/ML TS XAI/AIDS/10. ANOVA/Sample 1 Way ANOVA Test.ipynb +0 -119
  27. noshot/data/ML TS XAI/AIDS/10. ANOVA/Two Way ANOVA.ipynb +0 -138
  28. noshot/data/ML TS XAI/AIDS/10. ANOVA/reaction_time.csv +0 -5
  29. noshot/data/ML TS XAI/AIDS/10. ANOVA/sample_data.csv +0 -16
  30. noshot/data/ML TS XAI/AIDS/10. ANOVA/sleep_deprivation.csv +0 -4
  31. noshot/data/ML TS XAI/AIDS/11. Linear Regression/3_Linear.csv +0 -4802
  32. noshot/data/ML TS XAI/AIDS/11. Linear Regression/Linear Regression LAB.ipynb +0 -113
  33. noshot/data/ML TS XAI/AIDS/11. Linear Regression/Linear Regression New- sklearn.ipynb +0 -118
  34. noshot/data/ML TS XAI/AIDS/11. Linear Regression/Linear Regression.ipynb +0 -148
  35. noshot/data/ML TS XAI/AIDS/11. Linear Regression/house_rate.csv +0 -22
  36. noshot/data/ML TS XAI/AIDS/12. Logistic Regression/Logistic Regression New- sklearn.ipynb +0 -128
  37. noshot/data/ML TS XAI/AIDS/12. Logistic Regression/Logistic Regression.ipynb +0 -145
  38. noshot/data/ML TS XAI/AIDS/12. Logistic Regression/default.csv +0 -1001
  39. noshot/data/ML TS XAI/AIDS/12. Logistic Regression/hours_scores_records.csv +0 -101
  40. noshot/data/ML TS XAI/AIDS/2. Implement A Star And MA Star/(A) Astar.ipynb +0 -256
  41. noshot/data/ML TS XAI/AIDS/2. Implement A Star And MA Star/(B) IDAstar.ipynb +0 -157
  42. noshot/data/ML TS XAI/AIDS/2. Implement A Star And MA Star/(C) SMAstar.ipynb +0 -178
  43. noshot/data/ML TS XAI/AIDS/3. Genetic Algorithm/Genetic.ipynb +0 -95
  44. noshot/data/ML TS XAI/AIDS/4. Simulated Annealing/Simulated Annealing.ipynb +0 -74
  45. noshot/data/ML TS XAI/AIDS/4. Simulated Annealing/Sudoku Simulated Annealing.ipynb +0 -103
  46. noshot/data/ML TS XAI/AIDS/5. Alpha Beta Pruning/AlphaBetaPruning.ipynb +0 -182
  47. noshot/data/ML TS XAI/AIDS/6. Consraint Satisfaction Problems (CSP)/(A) CSP House Allocation.ipynb +0 -120
  48. noshot/data/ML TS XAI/AIDS/6. Consraint Satisfaction Problems (CSP)/(B) CSP Map Coloring.ipynb +0 -125
  49. noshot/data/ML TS XAI/AIDS/7. Random Sampling/Random Sampling.ipynb +0 -73
  50. noshot/data/ML TS XAI/AIDS/7. Random Sampling/height_weight_bmi.csv +0 -8389
  51. noshot/data/ML TS XAI/AIDS/8. Z Test/Z Test Hash Function.ipynb +0 -141
  52. noshot/data/ML TS XAI/AIDS/8. Z Test/Z Test.ipynb +0 -151
  53. noshot/data/ML TS XAI/AIDS/8. Z Test/height_weight_bmi.csv +0 -8389
  54. noshot/data/ML TS XAI/AIDS/9. T Test/1_heart.csv +0 -304
  55. noshot/data/ML TS XAI/AIDS/9. T Test/Independent T Test.ipynb +0 -119
  56. noshot/data/ML TS XAI/AIDS/9. T Test/Paired T Test.ipynb +0 -118
  57. noshot/data/ML TS XAI/AIDS/9. T Test/T Test Hash Function.ipynb +0 -142
  58. noshot/data/ML TS XAI/AIDS/9. T Test/T Test.ipynb +0 -158
  59. noshot/data/ML TS XAI/AIDS/9. T Test/height_weight_bmi.csv +0 -8389
  60. noshot/data/ML TS XAI/AIDS/9. T Test/iq_test.csv +0 -0
  61. noshot/data/ML TS XAI/AIDS/Others (AllinOne)/All In One.ipynb +0 -4581
  62. noshot/data/ML TS XAI/CN/1. Chat Application/chat.java +0 -81
  63. noshot/data/ML TS XAI/CN/1. Chat Application/output.png +0 -0
  64. noshot/data/ML TS XAI/CN/1. Chat Application/procedure.png +0 -0
  65. noshot/data/ML TS XAI/CN/10. Ethernet LAN IEEE 802.3/LAN.tcl +0 -65
  66. noshot/data/ML TS XAI/CN/10. Ethernet LAN IEEE 802.3/analysis.awk +0 -44
  67. noshot/data/ML TS XAI/CN/10. Ethernet LAN IEEE 802.3/output.png +0 -0
  68. noshot/data/ML TS XAI/CN/10. Ethernet LAN IEEE 802.3/procedure.png +0 -0
  69. noshot/data/ML TS XAI/CN/11. Wireless LAN IEEE 802.11/complexdcf.tcl +0 -229
  70. noshot/data/ML TS XAI/CN/11. Wireless LAN IEEE 802.11/output.png +0 -0
  71. noshot/data/ML TS XAI/CN/11. Wireless LAN IEEE 802.11/procedure.png +0 -0
  72. noshot/data/ML TS XAI/CN/2. File Transfer/file_to_send.txt +0 -2
  73. noshot/data/ML TS XAI/CN/2. File Transfer/filetransfer.java +0 -119
  74. noshot/data/ML TS XAI/CN/2. File Transfer/output.png +0 -0
  75. noshot/data/ML TS XAI/CN/2. File Transfer/procedure.png +0 -0
  76. noshot/data/ML TS XAI/CN/3. RMI (Remote Method Invocation)/Client.class +0 -0
  77. noshot/data/ML TS XAI/CN/3. RMI (Remote Method Invocation)/MyServerImpl.class +0 -0
  78. noshot/data/ML TS XAI/CN/3. RMI (Remote Method Invocation)/MyServerIntf.class +0 -0
  79. noshot/data/ML TS XAI/CN/3. RMI (Remote Method Invocation)/Server.class +0 -0
  80. noshot/data/ML TS XAI/CN/3. RMI (Remote Method Invocation)/output.png +0 -0
  81. noshot/data/ML TS XAI/CN/3. RMI (Remote Method Invocation)/procedure.png +0 -0
  82. noshot/data/ML TS XAI/CN/3. RMI (Remote Method Invocation)/rmi.java +0 -56
  83. noshot/data/ML TS XAI/CN/4. Wired Network/output.png +0 -0
  84. noshot/data/ML TS XAI/CN/4. Wired Network/procedure.png +0 -0
  85. noshot/data/ML TS XAI/CN/4. Wired Network/wired.awk +0 -25
  86. noshot/data/ML TS XAI/CN/4. Wired Network/wired.tcl +0 -81
  87. noshot/data/ML TS XAI/CN/5. Wireless Network/output.png +0 -0
  88. noshot/data/ML TS XAI/CN/5. Wireless Network/procedure.png +0 -0
  89. noshot/data/ML TS XAI/CN/5. Wireless Network/wireless.awk +0 -27
  90. noshot/data/ML TS XAI/CN/5. Wireless Network/wireless.tcl +0 -153
  91. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Sack And Vegas/analysis.awk +0 -27
  92. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Sack And Vegas/output.png +0 -0
  93. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Sack And Vegas/sack.tcl +0 -86
  94. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Sack And Vegas/vegas.tcl +0 -86
  95. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Tahoe And Reno/analysis.awk +0 -28
  96. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Tahoe And Reno/output.png +0 -0
  97. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Tahoe And Reno/reno.tcl +0 -78
  98. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Congestion Control/Tahoe And Reno/tahoe.tcl +0 -79
  99. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Flow Control/analysis.awk +0 -27
  100. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Flow Control/flow.tcl +0 -163
  101. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/TCP Flow Control/output.png +0 -0
  102. noshot/data/ML TS XAI/CN/6. TCP Flow And Congestion Control/procedure.png +0 -0
  103. noshot/data/ML TS XAI/CN/7. Link State And Distance Vector Routing/DV.tcl +0 -111
  104. noshot/data/ML TS XAI/CN/7. Link State And Distance Vector Routing/LS.tcl +0 -106
  105. noshot/data/ML TS XAI/CN/7. Link State And Distance Vector Routing/analysis.awk +0 -36
  106. noshot/data/ML TS XAI/CN/7. Link State And Distance Vector Routing/output.png +0 -0
  107. noshot/data/ML TS XAI/CN/7. Link State And Distance Vector Routing/procedure.png +0 -0
  108. noshot/data/ML TS XAI/CN/8. Multicast And Broadcast Routing/analysis.awk +0 -20
  109. noshot/data/ML TS XAI/CN/8. Multicast And Broadcast Routing/broadcast.tcl +0 -76
  110. noshot/data/ML TS XAI/CN/8. Multicast And Broadcast Routing/multicast.tcl +0 -103
  111. noshot/data/ML TS XAI/CN/8. Multicast And Broadcast Routing/output.png +0 -0
  112. noshot/data/ML TS XAI/CN/8. Multicast And Broadcast Routing/procedure.png +0 -0
  113. noshot/data/ML TS XAI/CN/9. DHCP/DHCP.java +0 -125
  114. noshot/data/ML TS XAI/CN/9. DHCP/output.png +0 -0
  115. noshot/data/ML TS XAI/CN/9. DHCP/procedure.png +0 -0
  116. noshot/data/ML TS XAI/NLP/NLP 1/1-Prereqs.py +0 -18
  117. noshot/data/ML TS XAI/NLP/NLP 1/2-Chi2test.py +0 -83
  118. noshot/data/ML TS XAI/NLP/NLP 1/2-T-test.py +0 -79
  119. noshot/data/ML TS XAI/NLP/NLP 1/3-WSD-nb.py +0 -53
  120. noshot/data/ML TS XAI/NLP/NLP 1/4-Hindle-Rooth.py +0 -53
  121. noshot/data/ML TS XAI/NLP/NLP 1/5-HMM-Trellis.py +0 -82
  122. noshot/data/ML TS XAI/NLP/NLP 1/6-HMM-Viterbi.py +0 -16
  123. noshot/data/ML TS XAI/NLP/NLP 1/7-PCFG-parsetree.py +0 -15
  124. noshot/data/ML TS XAI/NLP/NLP 1/Chi2test.ipynb +0 -285
  125. noshot/data/ML TS XAI/NLP/NLP 1/Hindle-Rooth.ipynb +0 -179
  126. noshot/data/ML TS XAI/NLP/NLP 1/Lab 10 - Text generator using LSTM.ipynb +0 -1461
  127. noshot/data/ML TS XAI/NLP/NLP 1/Lab 11 NMT.ipynb +0 -2307
  128. noshot/data/ML TS XAI/NLP/NLP 1/PCFG.ipynb +0 -134
  129. noshot/data/ML TS XAI/NLP/NLP 1/Prereqs.ipynb +0 -131
  130. noshot/data/ML TS XAI/NLP/NLP 1/T test.ipynb +0 -252
  131. noshot/data/ML TS XAI/NLP/NLP 1/TFIDF BOW.ipynb +0 -171
  132. noshot/data/ML TS XAI/NLP/NLP 1/Trellis.ipynb +0 -244
  133. noshot/data/ML TS XAI/NLP/NLP 1/WSD.ipynb +0 -645
  134. noshot/data/ML TS XAI/NLP/NLP 1/Word2Vec.ipynb +0 -93
  135. noshot/data/ML TS XAI/NLP/NLP 2/Lab01(tokenizer)/tokenizer.ipynb +0 -370
  136. noshot/data/ML TS XAI/NLP/NLP 2/Lab01(tokenizer)/training_tokenizer.txt +0 -6
  137. noshot/data/ML TS XAI/NLP/NLP 2/Lab02(stemming)/exp0.ipynb +0 -274
  138. noshot/data/ML TS XAI/NLP/NLP 2/Lab02(stemming)/lab2.ipynb +0 -905
  139. noshot/data/ML TS XAI/NLP/NLP 2/Lab02(stemming)/test.txt +0 -1
  140. noshot/data/ML TS XAI/NLP/NLP 2/Lab02(stemming)/tokenizing.ipynb +0 -272
  141. noshot/data/ML TS XAI/NLP/NLP 2/Lab03(parse-tree)/collocation.ipynb +0 -332
  142. noshot/data/ML TS XAI/NLP/NLP 2/Lab03(parse-tree)/lab3.ipynb +0 -549
  143. noshot/data/ML TS XAI/NLP/NLP 2/Lab03(parse-tree)/nlp.txt +0 -1
  144. noshot/data/ML TS XAI/NLP/NLP 2/Lab04(collocation)/Lab4-NLP-Exp-2.ipynb +0 -817
  145. noshot/data/ML TS XAI/NLP/NLP 2/Lab04(collocation)/collocation.ipynb +0 -332
  146. noshot/data/ML TS XAI/NLP/NLP 2/Lab05(WSD)/NLP-Lab-5-Exp3.ipynb +0 -231
  147. noshot/data/ML TS XAI/NLP/NLP 2/Lab05(WSD)/word-sense-disambiguation.ipynb +0 -507
  148. noshot/data/ML TS XAI/NLP/NLP 2/Lab06(additional-exercise)/lab6.ipynb +0 -134
  149. noshot/data/ML TS XAI/NLP/NLP 2/Lab07(HMM,Viterbi)/NLP Exp 4.ipynb +0 -255
  150. noshot/data/ML TS XAI/NLP/NLP 2/Lab07(HMM,Viterbi)/NLP_Exp_5.ipynb +0 -159
  151. noshot/data/ML TS XAI/NLP/NLP 2/Lab08(PCFG)/PCFG.ipynb +0 -282
  152. noshot/data/ML TS XAI/NLP/NLP 2/Lab09-Hindle-rooth&MLP/Lab 9 - MLP classifier.ipynb +0 -670
  153. noshot/data/ML TS XAI/NLP/NLP 2/Lab09-Hindle-rooth&MLP/MLP-alternative-code.ipynb +0 -613
  154. noshot/data/ML TS XAI/NLP/NLP 2/Lab09-Hindle-rooth&MLP/hindle-rooth-algorithm.ipynb +0 -74
  155. noshot/data/ML TS XAI/NLP/NLP 2/Lab10(LSTM)/Lab_10_Text_generator_using_LSTM.ipynb +0 -480
  156. noshot/data/ML TS XAI/NLP/NLP 2/Lab11(Viterbi-PCFG,Machine-translation)/Machine-translation.ipynb +0 -445
  157. noshot/data/ML TS XAI/NLP/NLP 2/Lab11(Viterbi-PCFG,Machine-translation)/Viterbi-PCFG.ipynb +0 -105
  158. noshot/data/ML TS XAI/NLP/NLP 2/Lab11(Viterbi-PCFG,Machine-translation)/corpora_tools.py +0 -87
  159. noshot/data/ML TS XAI/NLP/NLP 2/Lab11(Viterbi-PCFG,Machine-translation)/data_utils.py +0 -11
  160. noshot/data/ML TS XAI/NLP/NLP 2/Lab11(Viterbi-PCFG,Machine-translation)/train_translator.py +0 -83
  161. noshot/data/ML TS XAI/NLP/NLP 2/Lab12(Information-Extraction)/Information_Extraction.ipynb +0 -201
  162. noshot/data/ML TS XAI/NLP/NLP 3/Backtrack-without-Verbitri.ipynb +0 -185
  163. noshot/data/ML TS XAI/NLP/NLP 3/Backward-Procedure.ipynb +0 -597
  164. noshot/data/ML TS XAI/NLP/NLP 3/Bag_of.ipynb +0 -1422
  165. noshot/data/ML TS XAI/NLP/NLP 3/CYK-algorithm.ipynb +0 -1067
  166. noshot/data/ML TS XAI/NLP/NLP 3/Forward-Procedure.ipynb +0 -477
  167. noshot/data/ML TS XAI/NLP/NLP 3/LSTM.ipynb +0 -1290
  168. noshot/data/ML TS XAI/NLP/NLP 3/Lab 10 - Text generator using LSTM.ipynb +0 -1461
  169. noshot/data/ML TS XAI/NLP/NLP 3/Lab 11 NMT.ipynb +0 -2307
  170. noshot/data/ML TS XAI/NLP/NLP 3/NLP-LAB-4.ipynb +0 -216
  171. noshot/data/ML TS XAI/NLP/NLP 3/NLP-LAB-5.ipynb +0 -216
  172. noshot/data/ML TS XAI/NLP/NLP 3/abc.txt +0 -6
  173. noshot/data/ML TS XAI/NLP/NLP 3/ex-1-nltk.ipynb +0 -711
  174. noshot/data/ML TS XAI/NLP/NLP 3/ex-2-nlp.ipynb +0 -267
  175. noshot/data/ML TS XAI/NLP/NLP 3/exp8&9.ipynb +0 -305
  176. noshot/data/ML TS XAI/NLP/NLP 3/hind.ipynb +0 -287
  177. noshot/data/ML TS XAI/NLP/NLP 3/lab66.ipynb +0 -752
  178. noshot/data/ML TS XAI/NLP/NLP 3/leb_3.ipynb +0 -612
  179. noshot/data/ML TS XAI/NLP/NLP 3/naive_bayes_classifier.pkl +0 -0
  180. noshot/data/ML TS XAI/NLP/NLP 3/nlp_leb_1.ipynb +0 -3008
  181. noshot/data/ML TS XAI/NLP/NLP 3/nlp_leb_2.ipynb +0 -3095
  182. noshot/data/ML TS XAI/NLP/NLP 3/nlplab-9.ipynb +0 -295
  183. noshot/data/ML TS XAI/NLP/NLP 3/nltk-ex-4.ipynb +0 -506
  184. noshot/data/ML TS XAI/NLP/NLP 3/text1.txt +0 -48
  185. noshot/data/ML TS XAI/NLP/NLP 3/text2.txt +0 -8
  186. noshot/data/ML TS XAI/NLP/NLP 3/text3.txt +0 -48
  187. noshot/data/ML TS XAI/NLP/NLP 3/translation-rnn.ipynb +0 -812
  188. noshot/data/ML TS XAI/NLP/NLP 3/word2vector.ipynb +0 -173
  189. noshot/data/ML TS XAI/NLP/NLP 4/Backward Procedure Algorithm.ipynb +0 -179
  190. noshot/data/ML TS XAI/NLP/NLP 4/Chi Square Collocation.ipynb +0 -208
  191. noshot/data/ML TS XAI/NLP/NLP 4/Collocation (T test).ipynb +0 -188
  192. noshot/data/ML TS XAI/NLP/NLP 4/Experiment 1.ipynb +0 -437
  193. noshot/data/ML TS XAI/NLP/NLP 4/Forward Procedure Algorithm.ipynb +0 -132
  194. noshot/data/ML TS XAI/NLP/NLP 4/Hindle Rooth.ipynb +0 -414
  195. noshot/data/ML TS XAI/NLP/NLP 4/MachineTranslation.ipynb +0 -368
  196. noshot/data/ML TS XAI/NLP/NLP 4/Multi Layer Perceptron using MLPClassifier.ipynb +0 -86
  197. noshot/data/ML TS XAI/NLP/NLP 4/Multi Layer Perceptron using Tensorflow.ipynb +0 -112
  198. noshot/data/ML TS XAI/NLP/NLP 4/PCFG Inside Probability.ipynb +0 -451
  199. noshot/data/ML TS XAI/NLP/NLP 4/Text Generation using LSTM.ipynb +0 -297
  200. noshot/data/ML TS XAI/NLP/NLP 4/Viterbi.ipynb +0 -310
  201. noshot/data/ML TS XAI/NLP/NLP 4/Word Sense Disambiguation.ipynb +0 -335
  202. noshot/data/ML TS XAI/NLP/NLP 5/10.Text Generation using LSTM.ipynb +0 -316
  203. noshot/data/ML TS XAI/NLP/NLP 5/11.Machine Translation.ipynb +0 -868
  204. noshot/data/ML TS XAI/NLP/NLP 5/2.T and Chi2 Test.ipynb +0 -204
  205. noshot/data/ML TS XAI/NLP/NLP 5/3.Word Sense Diambiguation.ipynb +0 -234
  206. noshot/data/ML TS XAI/NLP/NLP 5/4.Hinddle and Rooth.ipynb +0 -128
  207. noshot/data/ML TS XAI/NLP/NLP 5/5.Forward and Backward.ipynb +0 -149
  208. noshot/data/ML TS XAI/NLP/NLP 5/6.Viterbi.ipynb +0 -111
  209. noshot/data/ML TS XAI/NLP/NLP 5/7.PCFG Parse Tree.ipynb +0 -134
  210. noshot/data/ML TS XAI/NLP/NLP 5/7.PCFG using cyk.ipynb +0 -101
  211. noshot/data/ML TS XAI/NLP/NLP 5/8.Bag of words and TF-IDF.ipynb +0 -310
  212. noshot/data/ML TS XAI/NLP/NLP 5/9.Word2Vector.ipynb +0 -78
  213. noshot/data/ML TS XAI/NLP/NLP 5/NLP ALL In One.ipynb +0 -2619
  214. noshot/data/ML TS XAI/NLP/NLP 5/sample1.txt +0 -15
  215. noshot/data/ML TS XAI/NLP/NLP 5/sample2.txt +0 -4
  216. noshot/data/ML TS XAI/NLP/NLP 5/word2vec_model.bin +0 -0
  217. noshot/data/ML TS XAI/NLP/NLP 6/1. Tokenize, Tagging, NER, Parse Tree.ipynb +0 -312
  218. noshot/data/ML TS XAI/NLP/NLP 6/2. T Test and Chi2 Test.ipynb +0 -185
  219. noshot/data/ML TS XAI/NLP/NLP 6/3. Naive Bayes WSD.ipynb +0 -199
  220. noshot/data/ML TS XAI/NLP/NLP 6/4. Hinddle and Rooth.ipynb +0 -151
  221. noshot/data/ML TS XAI/NLP/NLP 6/5 and 6 FWD, BWD, Viterbi.ipynb +0 -164
  222. noshot/data/ML TS XAI/NLP/NLP 6/7. PCFG using CYK.ipynb +0 -383
  223. noshot/data/ML TS XAI/NLP/NLP 6/8. BOW and TF-IDF.ipynb +0 -252
  224. noshot/data/ML TS XAI/Ubuntu CN Lab.iso +0 -0
  225. noshot-0.1.6.dist-info/RECORD +0 -216
  226. {noshot-0.1.6.dist-info → noshot-0.1.8.dist-info}/LICENSE.txt +0 -0
  227. {noshot-0.1.6.dist-info → noshot-0.1.8.dist-info}/WHEEL +0 -0
  228. {noshot-0.1.6.dist-info → noshot-0.1.8.dist-info}/top_level.txt +0 -0
noshot/data/ML TS XAI/NLP/NLP 3/nlp_leb_1.ipynb DELETED
@@ -1,3008 +0,0 @@
1
- {
2
- "cells": [
3
- {
4
- "cell_type": "code",
5
- "execution_count": 2,
6
- "id": "f4a37537-11b6-4b2b-b361-ea2dc19b3fb8",
7
- "metadata": {},
8
- "outputs": [],
9
- "source": [
10
- "import nltk"
11
- ]
12
- },
13
- {
14
- "cell_type": "code",
15
- "execution_count": 4,
16
- "id": "b21da007-fd69-4a4e-ae0d-b11909ebf77a",
17
- "metadata": {},
18
- "outputs": [
19
- {
20
- "name": "stdout",
21
- "output_type": "stream",
22
- "text": [
23
- "showing info https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/index.xml\n"
24
- ]
25
- },
26
- {
27
- "data": {
28
- "text/plain": [
29
- "True"
30
- ]
31
- },
32
- "execution_count": 4,
33
- "metadata": {},
34
- "output_type": "execute_result"
35
- }
36
- ],
37
- "source": [
38
- "nltk.download()"
39
- ]
40
- },
41
- {
42
- "cell_type": "code",
43
- "execution_count": 7,
44
- "id": "3e9a7c72-35da-4fe6-893f-3ea9a34d57f7",
45
- "metadata": {},
46
- "outputs": [
47
- {
48
- "data": {
49
- "text/plain": [
50
- "'eat'"
51
- ]
52
- },
53
- "execution_count": 7,
54
- "metadata": {},
55
- "output_type": "execute_result"
56
- }
57
- ],
58
- "source": [
59
- "from nltk.stem import PorterStemmer\n",
60
- "word_stemmer = PorterStemmer()\n",
61
- "word_stemmer.stem('eating')"
62
- ]
63
- },
64
- {
65
- "cell_type": "code",
66
- "execution_count": 8,
67
- "id": "36d8aed2-55ce-4df3-9007-035e952c0589",
68
- "metadata": {},
69
- "outputs": [
70
- {
71
- "data": {
72
- "text/plain": [
73
- "'walk'"
74
- ]
75
- },
76
- "execution_count": 8,
77
- "metadata": {},
78
- "output_type": "execute_result"
79
- }
80
- ],
81
- "source": [
82
- "word_stemmer.stem('walking')"
83
- ]
84
- },
85
- {
86
- "cell_type": "code",
87
- "execution_count": 10,
88
- "id": "72e3d595-ab06-4eac-8b57-63e9cc6592ec",
89
- "metadata": {},
90
- "outputs": [
91
- {
92
- "data": {
93
- "text/plain": [
94
- "['Hi', '!', ',', 'Welcome', 'to', 'nltk', '.']"
95
- ]
96
- },
97
- "execution_count": 10,
98
- "metadata": {},
99
- "output_type": "execute_result"
100
- }
101
- ],
102
- "source": [
103
- "from nltk.tokenize import word_tokenize\n",
104
- "word_tokenize('Hi!, Welcome to nltk.')"
105
- ]
106
- },
107
- {
108
- "cell_type": "code",
109
- "execution_count": 13,
110
- "id": "ef39c30b-fd2e-4b98-8efa-651dd253d43a",
111
- "metadata": {},
112
- "outputs": [
113
- {
114
- "data": {
115
- "text/plain": [
116
- "['This', 'is', 'your', 'first', 'lab', 'in', 'nltk']"
117
- ]
118
- },
119
- "execution_count": 13,
120
- "metadata": {},
121
- "output_type": "execute_result"
122
- }
123
- ],
124
- "source": [
125
- "from nltk.tokenize import TreebankWordTokenizer\n",
126
- "Tokenizer_wrd = TreebankWordTokenizer()\n",
127
- "Tokenizer_wrd.tokenize('This is your first lab in nltk')"
128
- ]
129
- },
130
- {
131
- "cell_type": "code",
132
- "execution_count": 19,
133
- "id": "d1ef9828-4d6f-478c-b5bd-a77e0535ecb3",
134
- "metadata": {},
135
- "outputs": [
136
- {
137
- "data": {
138
- "text/plain": [
139
- "['wo', \"n't\"]"
140
- ]
141
- },
142
- "execution_count": 19,
143
- "metadata": {},
144
- "output_type": "execute_result"
145
- }
146
- ],
147
- "source": [
148
- "from nltk.tokenize import word_tokenize\n",
149
- "word_tokenize('testing of word_tokenize...')\n",
150
- "word_tokenize(\"won't\")"
151
- ]
152
- },
153
- {
154
- "cell_type": "code",
155
- "execution_count": 20,
156
- "id": "015a6840-23fe-488e-85ec-16cbc845fb08",
157
- "metadata": {},
158
- "outputs": [
159
- {
160
- "data": {
161
- "text/plain": [
162
- "['testing', 'of', 'word_tokenize', '...']"
163
- ]
164
- },
165
- "execution_count": 20,
166
- "metadata": {},
167
- "output_type": "execute_result"
168
- }
169
- ],
170
- "source": [
171
- "word_tokenize('testing of word_tokenize...')"
172
- ]
173
- },
174
- {
175
- "cell_type": "code",
176
- "execution_count": 21,
177
- "id": "82bb2a79-a0d9-4048-85a7-55df69e32e57",
178
- "metadata": {},
179
- "outputs": [
180
- {
181
- "data": {
182
- "text/plain": [
183
- "['testing', 'of', 'word_tokenize', '...']"
184
- ]
185
- },
186
- "execution_count": 21,
187
- "metadata": {},
188
- "output_type": "execute_result"
189
- }
190
- ],
191
- "source": [
192
- "word_tokenize(\"won't\")\n",
193
- "word_tokenize('testing of word_tokenize...')"
194
- ]
195
- },
196
- {
197
- "cell_type": "code",
198
- "execution_count": 24,
199
- "id": "76a5b759-119e-431d-bd5b-eed9affe80a7",
200
- "metadata": {},
201
- "outputs": [
202
- {
203
- "data": {
204
- "text/plain": [
205
- "['I', \"'\", 'm', 'getting', 'started', 'with', 'nltk']"
206
- ]
207
- },
208
- "execution_count": 24,
209
- "metadata": {},
210
- "output_type": "execute_result"
211
- }
212
- ],
213
- "source": [
214
- "from nltk.tokenize import WordPunctTokenizer\n",
215
- "tokenizer = WordPunctTokenizer()\n",
216
- "tokenizer.tokenize(\"I'm getting started with nltk\")"
217
- ]
218
- },
219
- {
220
- "cell_type": "code",
221
- "execution_count": 27,
222
- "id": "750b2ae8-f34a-4200-8173-3dc9effdee44",
223
- "metadata": {},
224
- "outputs": [
225
- {
226
- "data": {
227
- "text/plain": [
228
- "[\"Let's understand the difference between sentence & word tokenizer.\",\n",
229
- " 'It is going to be a simple example.']"
230
- ]
231
- },
232
- "execution_count": 27,
233
- "metadata": {},
234
- "output_type": "execute_result"
235
- }
236
- ],
237
- "source": [
238
- "#tokenizing into sentences \n",
239
- "from nltk.tokenize import sent_tokenize\n",
240
- "text = \"Let's understand the difference between sentence & word tokenizer. It is going to be a simple example.\"\n",
241
- "sent_tokenize(text)"
242
- ]
243
- },
244
- {
245
- "cell_type": "code",
246
- "execution_count": 31,
247
- "id": "a48467e7-de59-441f-be18-3e4687dff281",
248
- "metadata": {},
249
- "outputs": [
250
- {
251
- "data": {
252
- "text/plain": [
253
- "[\"won't\", 'is', 'a', 'contraction']"
254
- ]
255
- },
256
- "execution_count": 31,
257
- "metadata": {},
258
- "output_type": "execute_result"
259
- }
260
- ],
261
- "source": [
262
- "#tokenizing using regular expressions\n",
263
- "from nltk.tokenize import RegexpTokenizer\n",
264
- "tokenizer = RegexpTokenizer(\"[\\w']+\")\n",
265
- "tokenizer.tokenize(\"won't is a contraction.\")"
266
- ]
267
- },
268
- {
269
- "cell_type": "code",
270
- "execution_count": 32,
271
- "id": "ba6ead99-e22a-4292-98d8-4bdc98b08d9f",
272
- "metadata": {},
273
- "outputs": [
274
- {
275
- "data": {
276
- "text/plain": [
277
- "[\"can't\", 'is', 'a', 'contraction']"
278
- ]
279
- },
280
- "execution_count": 32,
281
- "metadata": {},
282
- "output_type": "execute_result"
283
- }
284
- ],
285
- "source": [
286
- "tokenizer.tokenize(\"can't is a contraction.\")"
287
- ]
288
- },
289
- {
290
- "cell_type": "code",
291
- "execution_count": 35,
292
- "id": "c8ccffda-23d8-40f3-9854-6c7a6aeaf79c",
293
- "metadata": {},
294
- "outputs": [
295
- {
296
- "data": {
297
- "text/plain": [
298
- "[\"won't\", 'is', 'a', 'contraction.']"
299
- ]
300
- },
301
- "execution_count": 35,
302
- "metadata": {},
303
- "output_type": "execute_result"
304
- }
305
- ],
306
- "source": [
307
- "tokenizer = RegexpTokenizer('\\s+' , gaps = True)\n",
308
- "tokenizer.tokenize(\"won't is a contraction.\")"
309
- ]
310
- },
311
- {
312
- "cell_type": "code",
313
- "execution_count": 36,
314
- "id": "ecf65aa4-141e-42a7-ac9a-c2ee12355a95",
315
- "metadata": {},
316
- "outputs": [
317
- {
318
- "data": {
319
- "text/plain": [
320
- "[' ', ' ', ' ']"
321
- ]
322
- },
323
- "execution_count": 36,
324
- "metadata": {},
325
- "output_type": "execute_result"
326
- }
327
- ],
328
- "source": [
329
- "tokenizer = RegexpTokenizer('\\s+' , gaps = False)\n",
330
- "tokenizer.tokenize(\"won't is a contraction.\")"
331
- ]
332
- },
333
- {
334
- "cell_type": "code",
335
- "execution_count": 38,
336
- "id": "f14214b4-72d8-4248-a378-6b4004b93c52",
337
- "metadata": {},
338
- "outputs": [
339
- {
340
- "data": {
341
- "text/plain": [
342
- "[]"
343
- ]
344
- },
345
- "execution_count": 38,
346
- "metadata": {},
347
- "output_type": "execute_result"
348
- }
349
- ],
350
- "source": [
351
- "tokenizer = RegexpTokenizer('/s+' , gaps = False)\n",
352
- "tokenizer.tokenize(\"won't is a contraction.\")"
353
- ]
354
- },
355
- {
356
- "cell_type": "code",
357
- "execution_count": 39,
358
- "id": "07a6d8f2-18e2-447c-be2e-65d7a3f2aeb4",
359
- "metadata": {},
360
- "outputs": [
361
- {
362
- "data": {
363
- "text/plain": [
364
- "[\"won't is a contraction.\"]"
365
- ]
366
- },
367
- "execution_count": 39,
368
- "metadata": {},
369
- "output_type": "execute_result"
370
- }
371
- ],
372
- "source": [
373
- "tokenizer = RegexpTokenizer('/s+' , gaps = True)\n",
374
- "tokenizer.tokenize(\"won't is a contraction.\")"
375
- ]
376
- },
377
- {
378
- "cell_type": "code",
379
- "execution_count": 40,
380
- "id": "ef9658d8-30eb-4461-b5e7-cfc70c3d47ad",
381
- "metadata": {},
382
- "outputs": [],
383
- "source": [
384
- "from nltk.tokenize import PunktSentenceTokenizer\n",
385
- "from nltk.corpus import webtext"
386
- ]
387
- },
388
- {
389
- "cell_type": "code",
390
- "execution_count": 42,
391
- "id": "fa9e5107-8495-4660-b98d-0e6b21a37878",
392
- "metadata": {},
393
- "outputs": [],
394
- "source": [
395
- "text = webtext.raw('E://126156048/nltk_1.txt')"
396
- ]
397
- },
398
- {
399
- "cell_type": "code",
400
- "execution_count": 44,
401
- "id": "27625d3f-2a47-41c9-8952-690871c8bde8",
402
- "metadata": {},
403
- "outputs": [
404
- {
405
- "name": "stdout",
406
- "output_type": "stream",
407
- "text": [
408
- "Guy: How old are you?\n"
409
- ]
410
- }
411
- ],
412
- "source": [
413
- "sent_tokenizer = PunktSentenceTokenizer(text)\n",
414
- "sents_1 = sent_tokenizer.tokenize(text)\n",
415
- "print(sents_1[0])"
416
- ]
417
- },
418
- {
419
- "cell_type": "code",
420
- "execution_count": 45,
421
- "id": "f977af32-c7c1-4d13-8d7b-6cbc4605d088",
422
- "metadata": {},
423
- "outputs": [
424
- {
425
- "data": {
426
- "text/plain": [
427
- "['I', 'writer']"
428
- ]
429
- },
430
- "execution_count": 45,
431
- "metadata": {},
432
- "output_type": "execute_result"
433
- }
434
- ],
435
- "source": [
436
- "from nltk.corpus import stopwords\n",
437
- "english_stops = set(stopwords.words('english'))\n",
438
- "words = ['I', 'am', 'a', 'writer']\n",
439
- "[word for word in words if word not in english_stops]"
440
- ]
441
- },
442
- {
443
- "cell_type": "code",
444
- "execution_count": 46,
445
- "id": "963b8a9b-9fc0-43dc-be0a-059c5d781381",
446
- "metadata": {},
447
- "outputs": [
448
- {
449
- "data": {
450
- "text/plain": [
451
- "['arabic',\n",
452
- " 'azerbaijani',\n",
453
- " 'basque',\n",
454
- " 'bengali',\n",
455
- " 'catalan',\n",
456
- " 'chinese',\n",
457
- " 'danish',\n",
458
- " 'dutch',\n",
459
- " 'english',\n",
460
- " 'finnish',\n",
461
- " 'french',\n",
462
- " 'german',\n",
463
- " 'greek',\n",
464
- " 'hebrew',\n",
465
- " 'hinglish',\n",
466
- " 'hungarian',\n",
467
- " 'indonesian',\n",
468
- " 'italian',\n",
469
- " 'kazakh',\n",
470
- " 'nepali',\n",
471
- " 'norwegian',\n",
472
- " 'portuguese',\n",
473
- " 'romanian',\n",
474
- " 'russian',\n",
475
- " 'slovene',\n",
476
- " 'spanish',\n",
477
- " 'swedish',\n",
478
- " 'tajik',\n",
479
- " 'turkish']"
480
- ]
481
- },
482
- "execution_count": 46,
483
- "metadata": {},
484
- "output_type": "execute_result"
485
- }
486
- ],
487
- "source": [
488
- "from nltk.corpus import stopwords\n",
489
- "stopwords.fileids()"
490
- ]
491
- },
492
- {
493
- "cell_type": "code",
494
- "execution_count": 57,
495
- "id": "7ed982f7-4e3c-4288-995a-a4b4280c2f75",
496
- "metadata": {},
497
- "outputs": [
498
- {
499
- "name": "stdout",
500
- "output_type": "stream",
501
- "text": [
502
- "Guy: How old are you?\n",
503
- "Hipster girl: You know, I never answer that question. Because to me, it's about\n",
504
- "how mature you are, you know? I mean, a fourteen year old could be more mature\n",
505
- "than a twenty-five year old, right? I'm sorry, I just never answer that question.\n",
506
- "Guy: But, uh, you're older than eighteen, right?\n",
507
- "Hipster girl: Oh, yeah.\n"
508
- ]
509
- }
510
- ],
511
- "source": [
512
- "with open('E:/126156048/nltk_1.txt') as file:\n",
513
- " text = file.read()\n",
514
- "print(text)"
515
- ]
516
- },
517
- {
518
- "cell_type": "code",
519
- "execution_count": 59,
520
- "id": "a1d4bf78-16b6-483a-9f94-b8740f02c8d9",
521
- "metadata": {},
522
- "outputs": [
523
- {
524
- "data": {
525
- "text/plain": [
526
- "'dog.n.01'"
527
- ]
528
- },
529
- "execution_count": 59,
530
- "metadata": {},
531
- "output_type": "execute_result"
532
- }
533
- ],
534
- "source": [
535
- "from nltk.corpus import wordnet as wn\n",
536
- "syn = wn.synsets('dog')[0]\n",
537
- "syn.name()"
538
- ]
539
- },
540
- {
541
- "cell_type": "code",
542
- "execution_count": 63,
543
- "id": "e2bda52e-86c8-4ae1-a54b-54fa5cd24dd3",
544
- "metadata": {},
545
- "outputs": [
546
- {
547
- "name": "stdout",
548
- "output_type": "stream",
549
- "text": [
550
- "The Impact of Artificial Intelligence on Data Science\n",
551
- "Introduction\n",
552
- "In recent years, the convergence of artificial intelligence (AI) and data science has revolutionized numerous fields, leading to significant advancements in technology, healthcare, finance, and more. AI, with its ability to mimic human intelligence, and data science, which focuses on extracting knowledge from data, together form a powerful combination that drives innovation and efficiency. This essay explores the impact of AI on data science, highlighting key areas where AI has transformed data processing, analysis, and decision-making.\n",
553
- "\n",
554
- "Enhancing Data Processing Capabilities\n",
555
- "One of the primary ways AI has impacted data science is by enhancing data processing capabilities. Traditional data processing methods often struggle to handle the vast amounts of data generated in today's digital age. AI algorithms, particularly those involving machine learning (ML) and deep learning, can process and analyze massive datasets with \n"
556
- ]
557
- }
558
- ],
559
- "source": [
560
- "with open ('E:/126156048/text1.txt') as txt_file:\n",
561
- " essay = txt_file.read()\n",
562
- "print(essay[:1000])"
563
- ]
564
- },
565
- {
566
- "cell_type": "code",
567
- "execution_count": 66,
568
- "id": "dd688e03-80e5-42b2-b162-28f145a49ec0",
569
- "metadata": {},
570
- "outputs": [
571
- {
572
- "name": "stdout",
573
- "output_type": "stream",
574
- "text": [
575
- "Number of sentences: 52\n",
576
- "['The Impact of Artificial Intelligence on Data Science\\nIntroduction\\nIn recent years, the convergence of artificial intelligence (AI) and data science has revolutionized numerous fields, leading to significant advancements in technology, healthcare, finance, and more.', 'AI, with its ability to mimic human intelligence, and data science, which focuses on extracting knowledge from data, together form a powerful combination that drives innovation and efficiency.', 'This essay explores the impact of AI on data science, highlighting key areas where AI has transformed data processing, analysis, and decision-making.', 'Enhancing Data Processing Capabilities\\nOne of the primary ways AI has impacted data science is by enhancing data processing capabilities.', \"Traditional data processing methods often struggle to handle the vast amounts of data generated in today's digital age.\"]\n"
577
- ]
578
- }
579
- ],
580
- "source": [
581
- "#Tokenize the text into sentences\n",
582
- "sentences = sent_tokenize(essay)\n",
583
- "print(f\"Number of sentences: {len(sentences)}\")\n",
584
- "print(sentences[:5]) # Display first 5 sentences"
585
- ]
586
- },
587
- {
588
- "cell_type": "code",
589
- "execution_count": 68,
590
- "id": "e899a0a4-c5f5-4ab9-ae82-4d6ce88ce305",
591
- "metadata": {},
592
- "outputs": [
593
- {
594
- "name": "stdout",
595
- "output_type": "stream",
596
- "text": [
597
- "Number of words: 1229\n",
598
- "['The', 'Impact', 'of', 'Artificial', 'Intelligence', 'on', 'Data', 'Science', 'Introduction', 'In', 'recent', 'years', ',', 'the', 'convergence', 'of', 'artificial', 'intelligence', '(', 'AI']\n"
599
- ]
600
- }
601
- ],
602
- "source": [
603
- "#Tokenize the text into words\n",
604
- "words = word_tokenize(essay)\n",
605
- "print(f\"Number of words: {len(words)}\")\n",
606
- "print(words[:20]) # Display first 20 words"
607
- ]
608
- },
609
- {
610
- "cell_type": "code",
611
- "execution_count": 71,
612
- "id": "d927919d-6266-42ef-96df-b675a86d0be3",
613
- "metadata": {},
614
- "outputs": [
615
- {
616
- "name": "stdout",
617
- "output_type": "stream",
618
- "text": [
619
- "[(',', 84), ('and', 62), ('.', 52), ('data', 51), ('AI', 29), ('can', 23), ('of', 21), ('the', 21), ('to', 21), ('in', 20)]\n"
620
- ]
621
- }
622
- ],
623
- "source": [
624
- "#Perform frequency analysis\n",
625
- "from collections import Counter\n",
626
- "word_freq = Counter(words)\n",
627
- "print(word_freq.most_common(10)) # Display 10 most common words"
628
- ]
629
- },
630
- {
631
- "cell_type": "code",
632
- "execution_count": 72,
633
- "id": "8d2713f8-a9e7-405a-a888-d8feff394af1",
634
- "metadata": {},
635
- "outputs": [
636
- {
637
- "data": {
638
- "image/png": "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",
639
- "text/plain": [
640
- "<Figure size 640x480 with 1 Axes>"
641
- ]
642
- },
643
- "metadata": {},
644
- "output_type": "display_data"
645
- }
646
- ],
647
- "source": [
648
- "#Visualize the frequency of the top 10 words\n",
649
- "import matplotlib.pyplot as plt\n",
650
- "common_words = word_freq.most_common(10)\n",
651
- "labels, counts = zip(*common_words)\n",
652
- "plt.bar(labels, counts)\n",
653
- "plt.xlabel('Words')\n",
654
- "plt.ylabel('Frequency')\n",
655
- "plt.title('Top 10 Words by Frequency')\n",
656
- "plt.show()"
657
- ]
658
- },
659
- {
660
- "cell_type": "code",
661
- "execution_count": 78,
662
- "id": "13df25cb-b030-4550-96bf-dcf47db05665",
663
- "metadata": {},
664
- "outputs": [
665
- {
666
- "data": {
667
- "text/html": [
668
- "<div>\n",
669
- "<style scoped>\n",
670
- " .dataframe tbody tr th:only-of-type {\n",
671
- " vertical-align: middle;\n",
672
- " }\n",
673
- "\n",
674
- " .dataframe tbody tr th {\n",
675
- " vertical-align: top;\n",
676
- " }\n",
677
- "\n",
678
- " .dataframe thead th {\n",
679
- " text-align: right;\n",
680
- " }\n",
681
- "</style>\n",
682
- "<table border=\"1\" class=\"dataframe\">\n",
683
- " <thead>\n",
684
- " <tr style=\"text-align: right;\">\n",
685
- " <th></th>\n",
686
- " <th>Introduction</th>\n",
687
- " </tr>\n",
688
- " </thead>\n",
689
- " <tbody>\n",
690
- " <tr>\n",
691
- " <th>0</th>\n",
692
- " <td>In recent years, the convergence of artificial...</td>\n",
693
- " </tr>\n",
694
- " <tr>\n",
695
- " <th>1</th>\n",
696
- " <td>Enhancing Data Processing Capabilities</td>\n",
697
- " </tr>\n",
698
- " <tr>\n",
699
- " <th>2</th>\n",
700
- " <td>One of the primary ways AI has impacted data s...</td>\n",
701
- " </tr>\n",
702
- " <tr>\n",
703
- " <th>3</th>\n",
704
- " <td>Machine learning algorithms, for instance, can...</td>\n",
705
- " </tr>\n",
706
- " <tr>\n",
707
- " <th>4</th>\n",
708
- " <td>Automating Data Cleaning and Preparation</td>\n",
709
- " </tr>\n",
710
- " <tr>\n",
711
- " <th>5</th>\n",
712
- " <td>Data cleaning and preparation are crucial step...</td>\n",
713
- " </tr>\n",
714
- " <tr>\n",
715
- " <th>6</th>\n",
716
- " <td>For example, NLP algorithms can process unstru...</td>\n",
717
- " </tr>\n",
718
- " <tr>\n",
719
- " <th>7</th>\n",
720
- " <td>Advancing Predictive Analytics</td>\n",
721
- " </tr>\n",
722
- " <tr>\n",
723
- " <th>8</th>\n",
724
- " <td>Predictive analytics is a core component of da...</td>\n",
725
- " </tr>\n",
726
- " <tr>\n",
727
- " <th>9</th>\n",
728
- " <td>Machine learning models, such as regression, d...</td>\n",
729
- " </tr>\n",
730
- " <tr>\n",
731
- " <th>10</th>\n",
732
- " <td>Enabling Real-Time Data Analysis</td>\n",
733
- " </tr>\n",
734
- " <tr>\n",
735
- " <th>11</th>\n",
736
- " <td>The ability to analyze data in real-time is cr...</td>\n",
737
- " </tr>\n",
738
- " <tr>\n",
739
- " <th>12</th>\n",
740
- " <td>Stream processing involves analyzing data as i...</td>\n",
741
- " </tr>\n",
742
- " <tr>\n",
743
- " <th>13</th>\n",
744
- " <td>Edge computing brings data processing closer t...</td>\n",
745
- " </tr>\n",
746
- " <tr>\n",
747
- " <th>14</th>\n",
748
- " <td>Facilitating Advanced Data Visualization</td>\n",
749
- " </tr>\n",
750
- " <tr>\n",
751
- " <th>15</th>\n",
752
- " <td>Data visualization is a vital aspect of data s...</td>\n",
753
- " </tr>\n",
754
- " <tr>\n",
755
- " <th>16</th>\n",
756
- " <td>AI-driven data visualization tools can automat...</td>\n",
757
- " </tr>\n",
758
- " <tr>\n",
759
- " <th>17</th>\n",
760
- " <td>Transforming Natural Language Processing</td>\n",
761
- " </tr>\n",
762
- " <tr>\n",
763
- " <th>18</th>\n",
764
- " <td>Natural language processing (NLP) is a subfiel...</td>\n",
765
- " </tr>\n",
766
- " <tr>\n",
767
- " <th>19</th>\n",
768
- " <td>AI-powered NLP algorithms can perform tasks su...</td>\n",
769
- " </tr>\n",
770
- " <tr>\n",
771
- " <th>20</th>\n",
772
- " <td>Improving Decision-Making Processes</td>\n",
773
- " </tr>\n",
774
- " <tr>\n",
775
- " <th>21</th>\n",
776
- " <td>AI has fundamentally transformed decision-maki...</td>\n",
777
- " </tr>\n",
778
- " <tr>\n",
779
- " <th>22</th>\n",
780
- " <td>In supply chain management, for example, AI-dr...</td>\n",
781
- " </tr>\n",
782
- " <tr>\n",
783
- " <th>23</th>\n",
784
- " <td>Addressing Ethical and Bias Concerns</td>\n",
785
- " </tr>\n",
786
- " <tr>\n",
787
- " <th>24</th>\n",
788
- " <td>While AI has brought numerous benefits to data...</td>\n",
789
- " </tr>\n",
790
- " <tr>\n",
791
- " <th>25</th>\n",
792
- " <td>Efforts to mitigate bias in AI include develop...</td>\n",
793
- " </tr>\n",
794
- " <tr>\n",
795
- " <th>26</th>\n",
796
- " <td>Conclusion</td>\n",
797
- " </tr>\n",
798
- " <tr>\n",
799
- " <th>27</th>\n",
800
- " <td>The impact of artificial intelligence on data ...</td>\n",
801
- " </tr>\n",
802
- " </tbody>\n",
803
- "</table>\n",
804
- "</div>"
805
- ],
806
- "text/plain": [
807
- " Introduction\n",
808
- "0 In recent years, the convergence of artificial...\n",
809
- "1 Enhancing Data Processing Capabilities\n",
810
- "2 One of the primary ways AI has impacted data s...\n",
811
- "3 Machine learning algorithms, for instance, can...\n",
812
- "4 Automating Data Cleaning and Preparation\n",
813
- "5 Data cleaning and preparation are crucial step...\n",
814
- "6 For example, NLP algorithms can process unstru...\n",
815
- "7 Advancing Predictive Analytics\n",
816
- "8 Predictive analytics is a core component of da...\n",
817
- "9 Machine learning models, such as regression, d...\n",
818
- "10 Enabling Real-Time Data Analysis\n",
819
- "11 The ability to analyze data in real-time is cr...\n",
820
- "12 Stream processing involves analyzing data as i...\n",
821
- "13 Edge computing brings data processing closer t...\n",
822
- "14 Facilitating Advanced Data Visualization\n",
823
- "15 Data visualization is a vital aspect of data s...\n",
824
- "16 AI-driven data visualization tools can automat...\n",
825
- "17 Transforming Natural Language Processing\n",
826
- "18 Natural language processing (NLP) is a subfiel...\n",
827
- "19 AI-powered NLP algorithms can perform tasks su...\n",
828
- "20 Improving Decision-Making Processes\n",
829
- "21 AI has fundamentally transformed decision-maki...\n",
830
- "22 In supply chain management, for example, AI-dr...\n",
831
- "23 Addressing Ethical and Bias Concerns\n",
832
- "24 While AI has brought numerous benefits to data...\n",
833
- "25 Efforts to mitigate bias in AI include develop...\n",
834
- "26 Conclusion\n",
835
- "27 The impact of artificial intelligence on data ..."
836
- ]
837
- },
838
- "execution_count": 78,
839
- "metadata": {},
840
- "output_type": "execute_result"
841
- }
842
- ],
843
- "source": [
844
- "import pandas as pd\n",
845
- "df = pd.read_csv('E:/126156048/csv1.csv')\n",
846
- "df"
847
- ]
848
- },
849
- {
850
- "cell_type": "code",
851
- "execution_count": 79,
852
- "id": "c978776f-9029-4aef-bf5e-3d6a8721c667",
853
- "metadata": {},
854
- "outputs": [
855
- {
856
- "name": "stdout",
857
- "output_type": "stream",
858
- "text": [
859
- "['The Impact of Artificial Intelligence on Data Science']\n",
860
- "['Introduction']\n",
861
- "['In recent years', ' the convergence of artificial intelligence (AI) and data science has revolutionized numerous fields', ' leading to significant advancements in technology', ' healthcare', ' finance', ' and more. AI', ' with its ability to mimic human intelligence', ' and data science', ' which focuses on extracting knowledge from data', ' together form a powerful combination that drives innovation and efficiency. This essay explores the impact of AI on data science', ' highlighting key areas where AI has transformed data processing', ' analysis', ' and decision-making.']\n",
862
- "[]\n",
863
- "['Enhancing Data Processing Capabilities']\n",
864
- "[\"One of the primary ways AI has impacted data science is by enhancing data processing capabilities. Traditional data processing methods often struggle to handle the vast amounts of data generated in today's digital age. AI algorithms\", ' particularly those involving machine learning (ML) and deep learning', ' can process and analyze massive datasets with unprecedented speed and accuracy.']\n",
865
- "[]\n",
866
- "['Machine learning algorithms', ' for instance', ' can identify patterns and trends in large datasets that would be impossible for humans to detect manually. This capability is particularly valuable in fields such as healthcare', ' where analyzing patient data can lead to early diagnosis and personalized treatment plans. In finance', ' AI-driven data processing can detect fraudulent activities and predict market trends', ' enabling more informed investment decisions.']\n",
867
- "[]\n",
868
- "['Automating Data Cleaning and Preparation']\n",
869
- "['Data cleaning and preparation are crucial steps in the data science workflow', ' often accounting for a significant portion of the time spent on a project. AI has significantly improved the efficiency of these tasks through automation. Techniques such as natural language processing (NLP) and computer vision can automatically identify and correct errors', ' inconsistencies', ' and missing values in datasets.']\n",
870
- "[]\n",
871
- "['For example', ' NLP algorithms can process unstructured text data', ' extracting relevant information and transforming it into a structured format suitable for analysis. Similarly', ' computer vision techniques can analyze images and videos', ' identifying objects and extracting meaningful features. By automating these processes', ' AI reduces the manual effort required for data cleaning and preparation', ' allowing data scientists to focus on higher-level analytical tasks.']\n",
872
- "[]\n",
873
- "['Advancing Predictive Analytics']\n",
874
- "['Predictive analytics is a core component of data science', ' enabling organizations to make data-driven decisions by forecasting future trends and outcomes. AI has significantly advanced predictive analytics through the development of sophisticated algorithms that can accurately model complex relationships within data.']\n",
875
- "[]\n",
876
- "['Machine learning models', ' such as regression', ' decision trees', ' and neural networks', ' can predict outcomes based on historical data. These models continuously learn and improve as new data becomes available', ' enhancing their predictive accuracy over time. In industries like retail', ' predictive analytics powered by AI can optimize inventory management', ' forecast customer demand', ' and personalize marketing strategies.']\n",
877
- "[]\n",
878
- "['Enabling Real-Time Data Analysis']\n",
879
- "['The ability to analyze data in real-time is crucial in many applications', ' such as autonomous vehicles', ' financial trading', ' and cybersecurity. AI has enabled real-time data analysis by leveraging techniques like stream processing and edge computing.']\n",
880
- "[]\n",
881
- "['Stream processing involves analyzing data as it is generated', ' allowing for immediate insights and actions. AI algorithms can process streaming data from sensors', ' social media', ' and other sources', ' identifying anomalies and triggering alerts in real-time. In autonomous vehicles', ' real-time data analysis is essential for making split-second decisions to ensure safety and navigation.']\n",
882
- "[]\n",
883
- "['Edge computing brings data processing closer to the source of data generation', ' reducing latency and bandwidth requirements. AI models deployed on edge devices can analyze data locally', ' making real-time decisions without relying on centralized cloud servers. This capability is particularly valuable in scenarios where quick response times are critical', ' such as industrial automation and healthcare monitoring.']\n",
884
- "[]\n",
885
- "['Facilitating Advanced Data Visualization']\n",
886
- "['Data visualization is a vital aspect of data science', ' enabling stakeholders to understand complex data through graphical representations. AI has facilitated advanced data visualization techniques that provide deeper insights and more intuitive understanding.']\n",
887
- "[]\n",
888
- "['AI-driven data visualization tools can automatically generate visualizations based on the characteristics of the data', ' highlighting key trends and outliers. These tools can also create interactive dashboards that allow users to explore data dynamically', ' adjusting parameters and filters to uncover hidden patterns. For example', ' AI-powered visualization platforms in business intelligence can present sales data in interactive charts and graphs', ' enabling executives to make data-driven decisions quickly.']\n",
889
- "[]\n",
890
- "['Transforming Natural Language Processing']\n",
891
- "['Natural language processing (NLP) is a subfield of AI that focuses on the interaction between computers and human language. NLP has transformed data science by enabling the analysis of unstructured text data', ' which constitutes a significant portion of the data generated today.']\n",
892
- "[]\n",
893
- "['AI-powered NLP algorithms can perform tasks such as sentiment analysis', ' entity recognition', ' and text summarization. These capabilities are invaluable in applications like social media monitoring', ' where analyzing customer sentiments and trends can inform marketing strategies. In healthcare', ' NLP can process clinical notes and research papers', ' extracting valuable insights for medical research and patient care.']\n",
894
- "[]\n",
895
- "['Improving Decision-Making Processes']\n",
896
- "['AI has fundamentally transformed decision-making processes in data science by providing more accurate and actionable insights. Decision support systems powered by AI can analyze vast amounts of data', ' evaluate multiple scenarios', ' and recommend optimal courses of action.']\n",
897
- "[]\n",
898
- "['In supply chain management', ' for example', ' AI-driven decision support systems can optimize inventory levels', ' predict demand fluctuations', ' and identify potential disruptions. In the financial sector', ' AI algorithms can assess credit risks', ' detect fraudulent activities', ' and optimize investment portfolios. By leveraging AI', ' organizations can make more informed and data-driven decisions', ' reducing risks and enhancing operational efficiency.']\n",
899
- "[]\n",
900
- "['Addressing Ethical and Bias Concerns']\n",
901
- "['While AI has brought numerous benefits to data science', ' it also raises important ethical and bias concerns. AI algorithms can inadvertently perpetuate biases present in the training data', ' leading to unfair or discriminatory outcomes. Addressing these issues is crucial to ensure the responsible and ethical use of AI in data science.']\n",
902
- "[]\n",
903
- "['Efforts to mitigate bias in AI include developing fairness-aware algorithms', ' ensuring diverse and representative training data', ' and implementing transparent and explainable AI models. Additionally', ' ethical guidelines and regulations are being established to govern the use of AI in various applications', ' ensuring that AI systems are designed and deployed in a manner that respects human rights and societal values.']\n",
904
- "[]\n",
905
- "['Conclusion']\n",
906
- "['The impact of artificial intelligence on data science is profound and far-reaching. AI has enhanced data processing capabilities', ' automated data cleaning and preparation', ' advanced predictive analytics', ' enabled real-time data analysis', ' facilitated advanced data visualization', ' transformed natural language processing', ' improved decision-making processes', ' and addressed ethical concerns. As AI continues to evolve', ' its integration with data science will drive further innovation and transformation across various industries. Embracing the synergy between AI and data science is essential for organizations seeking to harness the full potential of their data and stay competitive in an increasingly data-driven world.']\n"
907
- ]
908
- }
909
- ],
910
- "source": [
911
- "import csv\n",
912
- "with open ('E:/126156048/text1.txt', mode = 'r') as csv_file:\n",
913
- " csv_contents = csv.reader(csv_file)\n",
914
- " for lines in csv_contents:\n",
915
- " print(lines)"
916
- ]
917
- },
918
- {
919
- "cell_type": "code",
920
- "execution_count": 118,
921
- "id": "cec61606-b10e-4838-a5c7-8ceb2a948a4b",
922
- "metadata": {},
923
- "outputs": [
924
- {
925
- "name": "stdout",
926
- "output_type": "stream",
927
- "text": [
928
- "Number of unique words: 437\n",
929
- "Word Frequency Analysis:\n",
930
- "introduction: 1\n",
931
- "in: 27\n",
932
- "recent: 1\n",
933
- "years: 1\n",
934
- "the: 23\n",
935
- "convergence: 1\n",
936
- "of: 20\n",
937
- "artificial: 2\n",
938
- "intelligence: 4\n",
939
- "ai: 29\n",
940
- "and: 62\n",
941
- "data: 57\n",
942
- "science: 14\n",
943
- "has: 11\n",
944
- "revolutionized: 1\n",
945
- "numerous: 2\n",
946
- "fields: 2\n",
947
- "leading: 2\n",
948
- "to: 21\n",
949
- "significant: 3\n",
950
- "advancements: 1\n",
951
- "technology: 1\n",
952
- "healthcare: 4\n",
953
- "finance: 2\n",
954
- "more: 5\n",
955
- "with: 3\n",
956
- "its: 2\n",
957
- "ability: 2\n",
958
- "mimic: 1\n",
959
- "human: 3\n",
960
- "which: 2\n",
961
- "focuses: 2\n",
962
- "on: 10\n",
963
- "extracting: 4\n",
964
- "knowledge: 1\n",
965
- "from: 2\n",
966
- "together: 1\n",
967
- "form: 1\n",
968
- "a: 9\n",
969
- "powerful: 1\n",
970
- "combination: 1\n",
971
- "that: 8\n",
972
- "drives: 1\n",
973
- "innovation: 2\n",
974
- "efficiency: 3\n",
975
- "this: 3\n",
976
- "essay: 1\n",
977
- "explores: 1\n",
978
- "impact: 2\n",
979
- "highlighting: 2\n",
980
- "key: 2\n",
981
- "areas: 1\n",
982
- "where: 4\n",
983
- "transformed: 4\n",
984
- "processing: 13\n",
985
- "analysis: 8\n",
986
- "decision-making: 4\n",
987
- "enhancing: 4\n",
988
- "capabilities: 4\n",
989
- "one: 1\n",
990
- "primary: 1\n",
991
- "ways: 1\n",
992
- "impacted: 1\n",
993
- "is: 12\n",
994
- "by: 9\n",
995
- "traditional: 1\n",
996
- "methods: 1\n",
997
- "often: 2\n",
998
- "struggle: 1\n",
999
- "handle: 1\n",
1000
- "vast: 2\n",
1001
- "amounts: 2\n",
1002
- "generated: 3\n",
1003
- "today's: 1\n",
1004
- "digital: 1\n",
1005
- "age: 1\n",
1006
- "algorithms: 9\n",
1007
- "particularly: 3\n",
1008
- "those: 1\n",
1009
- "involving: 1\n",
1010
- "machine: 3\n",
1011
- "learning: 4\n",
1012
- "ml: 1\n",
1013
- "deep: 1\n",
1014
- "can: 23\n",
1015
- "process: 4\n",
1016
- "analyze: 5\n",
1017
- "massive: 1\n",
1018
- "datasets: 3\n",
1019
- "unprecedented: 1\n",
1020
- "speed: 1\n",
1021
- "accuracy: 2\n",
1022
- "for: 12\n",
1023
- "instance: 1\n",
1024
- "identify: 3\n",
1025
- "patterns: 2\n",
1026
- "trends: 5\n",
1027
- "large: 1\n",
1028
- "would: 1\n",
1029
- "be: 1\n",
1030
- "impossible: 1\n",
1031
- "humans: 1\n",
1032
- "detect: 3\n",
1033
- "manually: 1\n",
1034
- "capability: 2\n",
1035
- "valuable: 3\n",
1036
- "such: 6\n",
1037
- "as: 9\n",
1038
- "analyzing: 3\n",
1039
- "patient: 2\n",
1040
- "lead: 1\n",
1041
- "early: 1\n",
1042
- "diagnosis: 1\n",
1043
- "personalized: 1\n",
1044
- "treatment: 1\n",
1045
- "plans: 1\n",
1046
- "ai-driven: 3\n",
1047
- "fraudulent: 2\n",
1048
- "activities: 2\n",
1049
- "predict: 3\n",
1050
- "market: 1\n",
1051
- "enabling: 6\n",
1052
- "informed: 2\n",
1053
- "investment: 2\n",
1054
- "decisions: 6\n",
1055
- "automating: 2\n",
1056
- "cleaning: 4\n",
1057
- "preparation: 4\n",
1058
- "are: 5\n",
1059
- "crucial: 3\n",
1060
- "steps: 1\n",
1061
- "workflow: 1\n",
1062
- "accounting: 1\n",
1063
- "portion: 2\n",
1064
- "time: 2\n",
1065
- "spent: 1\n",
1066
- "project: 1\n",
1067
- "significantly: 2\n",
1068
- "improved: 2\n",
1069
- "these: 6\n",
1070
- "tasks: 3\n",
1071
- "through: 3\n",
1072
- "automation: 2\n",
1073
- "techniques: 4\n",
1074
- "natural: 4\n",
1075
- "language: 5\n",
1076
- "nlp: 6\n",
1077
- "computer: 2\n",
1078
- "vision: 2\n",
1079
- "automatically: 2\n",
1080
- "correct: 1\n",
1081
- "errors: 1\n",
1082
- "inconsistencies: 1\n",
1083
- "missing: 1\n",
1084
- "values: 2\n",
1085
- "example: 3\n",
1086
- "unstructured: 2\n",
1087
- "text: 3\n",
1088
- "relevant: 1\n",
1089
- "information: 1\n",
1090
- "transforming: 2\n",
1091
- "it: 3\n",
1092
- "into: 1\n",
1093
- "structured: 1\n",
1094
- "format: 1\n",
1095
- "suitable: 1\n",
1096
- "similarly: 1\n",
1097
- "images: 1\n",
1098
- "videos: 1\n",
1099
- "identifying: 2\n",
1100
- "objects: 1\n",
1101
- "meaningful: 1\n",
1102
- "features: 1\n",
1103
- "processes: 4\n",
1104
- "reduces: 1\n",
1105
- "manual: 1\n",
1106
- "effort: 1\n",
1107
- "required: 1\n",
1108
- "allowing: 2\n",
1109
- "scientists: 1\n",
1110
- "focus: 1\n",
1111
- "higher-level: 1\n",
1112
- "analytical: 1\n",
1113
- "advancing: 1\n",
1114
- "predictive: 6\n",
1115
- "analytics: 5\n",
1116
- "core: 1\n",
1117
- "component: 1\n",
1118
- "organizations: 3\n",
1119
- "make: 3\n",
1120
- "data-driven: 4\n",
1121
- "forecasting: 1\n",
1122
- "future: 1\n",
1123
- "outcomes: 3\n",
1124
- "advanced: 5\n",
1125
- "development: 1\n",
1126
- "sophisticated: 1\n",
1127
- "accurately: 1\n",
1128
- "model: 1\n",
1129
- "complex: 2\n",
1130
- "relationships: 1\n",
1131
- "within: 1\n",
1132
- "models: 4\n",
1133
- "regression: 1\n",
1134
- "decision: 3\n",
1135
- "trees: 1\n",
1136
- "neural: 1\n",
1137
- "networks: 1\n",
1138
- "based: 2\n",
1139
- "historical: 1\n",
1140
- "continuously: 1\n",
1141
- "learn: 1\n",
1142
- "improve: 1\n",
1143
- "new: 1\n",
1144
- "becomes: 1\n",
1145
- "available: 1\n",
1146
- "their: 2\n",
1147
- "over: 1\n",
1148
- "industries: 2\n",
1149
- "like: 3\n",
1150
- "retail: 1\n",
1151
- "powered: 2\n",
1152
- "optimize: 3\n",
1153
- "inventory: 2\n",
1154
- "management: 2\n",
1155
- "forecast: 1\n",
1156
- "customer: 2\n",
1157
- "demand: 2\n",
1158
- "personalize: 1\n",
1159
- "marketing: 2\n",
1160
- "strategies: 2\n",
1161
- "real-time: 7\n",
1162
- "many: 1\n",
1163
- "applications: 3\n",
1164
- "autonomous: 2\n",
1165
- "vehicles: 2\n",
1166
- "financial: 2\n",
1167
- "trading: 1\n",
1168
- "cybersecurity: 1\n",
1169
- "enabled: 2\n",
1170
- "leveraging: 2\n",
1171
- "stream: 2\n",
1172
- "edge: 3\n",
1173
- "computing: 2\n",
1174
- "involves: 1\n",
1175
- "immediate: 1\n",
1176
- "insights: 4\n",
1177
- "actions: 1\n",
1178
- "streaming: 1\n",
1179
- "sensors: 1\n",
1180
- "social: 2\n",
1181
- "media: 2\n",
1182
- "other: 1\n",
1183
- "sources: 1\n",
1184
- "anomalies: 1\n",
1185
- "triggering: 1\n",
1186
- "alerts: 1\n",
1187
- "essential: 2\n",
1188
- "making: 2\n",
1189
- "split-second: 1\n",
1190
- "ensure: 2\n",
1191
- "safety: 1\n",
1192
- "navigation: 1\n",
1193
- "brings: 1\n",
1194
- "closer: 1\n",
1195
- "source: 1\n",
1196
- "generation: 1\n",
1197
- "reducing: 2\n",
1198
- "latency: 1\n",
1199
- "bandwidth: 1\n",
1200
- "requirements: 1\n",
1201
- "deployed: 2\n",
1202
- "devices: 1\n",
1203
- "locally: 1\n",
1204
- "without: 1\n",
1205
- "relying: 1\n",
1206
- "centralized: 1\n",
1207
- "cloud: 1\n",
1208
- "servers: 1\n",
1209
- "scenarios: 2\n",
1210
- "quick: 1\n",
1211
- "response: 1\n",
1212
- "times: 1\n",
1213
- "critical: 1\n",
1214
- "industrial: 1\n",
1215
- "monitoring: 2\n",
1216
- "facilitating: 1\n",
1217
- "visualization: 6\n",
1218
- "vital: 1\n",
1219
- "aspect: 1\n",
1220
- "stakeholders: 1\n",
1221
- "understand: 1\n",
1222
- "graphical: 1\n",
1223
- "representations: 1\n",
1224
- "facilitated: 2\n",
1225
- "provide: 1\n",
1226
- "deeper: 1\n",
1227
- "intuitive: 1\n",
1228
- "understanding: 1\n",
1229
- "tools: 2\n",
1230
- "generate: 1\n",
1231
- "visualizations: 1\n",
1232
- "characteristics: 1\n",
1233
- "outliers: 1\n",
1234
- "also: 2\n",
1235
- "create: 1\n",
1236
- "interactive: 2\n",
1237
- "dashboards: 1\n",
1238
- "allow: 1\n",
1239
- "users: 1\n",
1240
- "explore: 1\n",
1241
- "dynamically: 1\n",
1242
- "adjusting: 1\n",
1243
- "parameters: 1\n",
1244
- "filters: 1\n",
1245
- "uncover: 1\n",
1246
- "hidden: 1\n",
1247
- "ai-powered: 2\n",
1248
- "platforms: 1\n",
1249
- "business: 1\n",
1250
- "present: 2\n",
1251
- "sales: 1\n",
1252
- "charts: 1\n",
1253
- "graphs: 1\n",
1254
- "executives: 1\n",
1255
- "quickly: 1\n",
1256
- "subfield: 1\n",
1257
- "interaction: 1\n",
1258
- "between: 2\n",
1259
- "computers: 1\n",
1260
- "constitutes: 1\n",
1261
- "today: 1\n",
1262
- "perform: 1\n",
1263
- "sentiment: 1\n",
1264
- "entity: 1\n",
1265
- "recognition: 1\n",
1266
- "summarization: 1\n",
1267
- "invaluable: 1\n",
1268
- "sentiments: 1\n",
1269
- "inform: 1\n",
1270
- "clinical: 1\n",
1271
- "notes: 1\n",
1272
- "research: 2\n",
1273
- "papers: 1\n",
1274
- "medical: 1\n",
1275
- "care: 1\n",
1276
- "improving: 1\n",
1277
- "fundamentally: 1\n",
1278
- "providing: 1\n",
1279
- "accurate: 1\n",
1280
- "actionable: 1\n",
1281
- "support: 2\n",
1282
- "systems: 3\n",
1283
- "evaluate: 1\n",
1284
- "multiple: 1\n",
1285
- "recommend: 1\n",
1286
- "optimal: 1\n",
1287
- "courses: 1\n",
1288
- "action: 1\n",
1289
- "supply: 1\n",
1290
- "chain: 1\n",
1291
- "levels: 1\n",
1292
- "fluctuations: 1\n",
1293
- "potential: 2\n",
1294
- "disruptions: 1\n",
1295
- "sector: 1\n",
1296
- "assess: 1\n",
1297
- "credit: 1\n",
1298
- "risks: 2\n",
1299
- "portfolios: 1\n",
1300
- "operational: 1\n",
1301
- "addressing: 2\n",
1302
- "ethical: 5\n",
1303
- "bias: 3\n",
1304
- "concerns: 3\n",
1305
- "while: 1\n",
1306
- "brought: 1\n",
1307
- "benefits: 1\n",
1308
- "raises: 1\n",
1309
- "important: 1\n",
1310
- "inadvertently: 1\n",
1311
- "perpetuate: 1\n",
1312
- "biases: 1\n",
1313
- "training: 2\n",
1314
- "unfair: 1\n",
1315
- "or: 1\n",
1316
- "discriminatory: 1\n",
1317
- "issues: 1\n",
1318
- "responsible: 1\n",
1319
- "use: 2\n",
1320
- "efforts: 1\n",
1321
- "mitigate: 1\n",
1322
- "include: 1\n",
1323
- "developing: 1\n",
1324
- "fairness-aware: 1\n",
1325
- "ensuring: 2\n",
1326
- "diverse: 1\n",
1327
- "representative: 1\n",
1328
- "implementing: 1\n",
1329
- "transparent: 1\n",
1330
- "explainable: 1\n",
1331
- "additionally: 1\n",
1332
- "guidelines: 1\n",
1333
- "regulations: 1\n",
1334
- "being: 1\n",
1335
- "established: 1\n",
1336
- "govern: 1\n",
1337
- "various: 2\n",
1338
- "designed: 1\n",
1339
- "manner: 1\n",
1340
- "respects: 1\n",
1341
- "rights: 1\n",
1342
- "societal: 1\n",
1343
- "conclusion: 1\n",
1344
- "profound: 1\n",
1345
- "far-reaching: 1\n",
1346
- "enhanced: 1\n",
1347
- "automated: 1\n",
1348
- "addressed: 1\n",
1349
- "continues: 1\n",
1350
- "evolve: 1\n",
1351
- "integration: 1\n",
1352
- "will: 1\n",
1353
- "drive: 1\n",
1354
- "further: 1\n",
1355
- "transformation: 1\n",
1356
- "across: 1\n",
1357
- "embracing: 1\n",
1358
- "synergy: 1\n",
1359
- "seeking: 1\n",
1360
- "harness: 1\n",
1361
- "full: 1\n",
1362
- "stay: 1\n",
1363
- "competitive: 1\n",
1364
- "an: 1\n",
1365
- "increasingly: 1\n",
1366
- "world: 1\n"
1367
- ]
1368
- }
1369
- ],
1370
- "source": [
1371
- "# Function to read the CSV file and return the text content\n",
1372
- "def read_csv_file(file_path):\n",
1373
- " essay_text = \"\"\n",
1374
- " with open(file_path, 'r') as file:\n",
1375
- " for line in file:\n",
1376
- " # Remove newline characters and quotes, then append to essay_text\n",
1377
- " essay_text += line.strip().replace('\"', '') + \" \"\n",
1378
- " return essay_text\n",
1379
- "\n",
1380
- "# Function to tokenize the text into words\n",
1381
- "def tokenize(text):\n",
1382
- " words = text.split()\n",
1383
- " return [word.strip(\".,!?\\\"'()[]{}:;\") for word in words]\n",
1384
- "\n",
1385
- "# Function to perform frequency analysis\n",
1386
- "def frequency_analysis(words):\n",
1387
- " frequency = {}\n",
1388
- " for word in words:\n",
1389
- " if word.lower() in frequency:\n",
1390
- " frequency[word.lower()] += 1\n",
1391
- " else:\n",
1392
- " frequency[word.lower()] = 1\n",
1393
- " return frequency\n",
1394
- "\n",
1395
- "# Load the essay text from the CSV file\n",
1396
- "essay_text = read_csv_file('E:/126156048/csv1.csv')\n",
1397
- "\n",
1398
- "# Tokenize the text into words\n",
1399
- "words = tokenize(essay_text)\n",
1400
- "\n",
1401
- "# Perform frequency analysis\n",
1402
- "word_freq = frequency_analysis(words)\n",
1403
- "\n",
1404
- "# Find the number of unique words\n",
1405
- "num_unique_words = len(word_freq)\n",
1406
- "\n",
1407
- "# Display the number of unique words\n",
1408
- "print(f\"Number of unique words: {num_unique_words}\")\n",
1409
- "\n",
1410
- "# Display the frequency of each word\n",
1411
- "print(\"Word Frequency Analysis:\")\n",
1412
- "for word, freq in word_freq.items():\n",
1413
- " print(f\"{word}: {freq}\")\n"
1414
- ]
1415
- },
1416
- {
1417
- "cell_type": "code",
1418
- "execution_count": 119,
1419
- "id": "242946ce-3399-4fa4-b60a-4839b91c0a1d",
1420
- "metadata": {},
1421
- "outputs": [
1422
- {
1423
- "name": "stdout",
1424
- "output_type": "stream",
1425
- "text": [
1426
- "Number of unique words: 437\n",
1427
- "Word Frequency Analysis:\n",
1428
- "introduction: 1\n",
1429
- "in: 27\n",
1430
- "recent: 1\n",
1431
- "years: 1\n",
1432
- "the: 23\n",
1433
- "convergence: 1\n",
1434
- "of: 20\n",
1435
- "artificial: 2\n",
1436
- "intelligence: 4\n",
1437
- "ai: 29\n",
1438
- "and: 62\n",
1439
- "data: 57\n",
1440
- "science: 14\n",
1441
- "has: 11\n",
1442
- "revolutionized: 1\n",
1443
- "numerous: 2\n",
1444
- "fields: 2\n",
1445
- "leading: 2\n",
1446
- "to: 21\n",
1447
- "significant: 3\n",
1448
- "advancements: 1\n",
1449
- "technology: 1\n",
1450
- "healthcare: 4\n",
1451
- "finance: 2\n",
1452
- "more: 5\n",
1453
- "with: 3\n",
1454
- "its: 2\n",
1455
- "ability: 2\n",
1456
- "mimic: 1\n",
1457
- "human: 3\n",
1458
- "which: 2\n",
1459
- "focuses: 2\n",
1460
- "on: 10\n",
1461
- "extracting: 4\n",
1462
- "knowledge: 1\n",
1463
- "from: 2\n",
1464
- "together: 1\n",
1465
- "form: 1\n",
1466
- "a: 9\n",
1467
- "powerful: 1\n",
1468
- "combination: 1\n",
1469
- "that: 8\n",
1470
- "drives: 1\n",
1471
- "innovation: 2\n",
1472
- "efficiency: 3\n",
1473
- "this: 3\n",
1474
- "essay: 1\n",
1475
- "explores: 1\n",
1476
- "impact: 2\n",
1477
- "highlighting: 2\n",
1478
- "key: 2\n",
1479
- "areas: 1\n",
1480
- "where: 4\n",
1481
- "transformed: 4\n",
1482
- "processing: 13\n",
1483
- "analysis: 8\n",
1484
- "decision-making: 4\n",
1485
- "enhancing: 4\n",
1486
- "capabilities: 4\n",
1487
- "one: 1\n",
1488
- "primary: 1\n",
1489
- "ways: 1\n",
1490
- "impacted: 1\n",
1491
- "is: 12\n",
1492
- "by: 9\n",
1493
- "traditional: 1\n",
1494
- "methods: 1\n",
1495
- "often: 2\n",
1496
- "struggle: 1\n",
1497
- "handle: 1\n",
1498
- "vast: 2\n",
1499
- "amounts: 2\n",
1500
- "generated: 3\n",
1501
- "today's: 1\n",
1502
- "digital: 1\n",
1503
- "age: 1\n",
1504
- "algorithms: 9\n",
1505
- "particularly: 3\n",
1506
- "those: 1\n",
1507
- "involving: 1\n",
1508
- "machine: 3\n",
1509
- "learning: 4\n",
1510
- "ml: 1\n",
1511
- "deep: 1\n",
1512
- "can: 23\n",
1513
- "process: 4\n",
1514
- "analyze: 5\n",
1515
- "massive: 1\n",
1516
- "datasets: 3\n",
1517
- "unprecedented: 1\n",
1518
- "speed: 1\n",
1519
- "accuracy: 2\n",
1520
- "for: 12\n",
1521
- "instance: 1\n",
1522
- "identify: 3\n",
1523
- "patterns: 2\n",
1524
- "trends: 5\n",
1525
- "large: 1\n",
1526
- "would: 1\n",
1527
- "be: 1\n",
1528
- "impossible: 1\n",
1529
- "humans: 1\n",
1530
- "detect: 3\n",
1531
- "manually: 1\n",
1532
- "capability: 2\n",
1533
- "valuable: 3\n",
1534
- "such: 6\n",
1535
- "as: 9\n",
1536
- "analyzing: 3\n",
1537
- "patient: 2\n",
1538
- "lead: 1\n",
1539
- "early: 1\n",
1540
- "diagnosis: 1\n",
1541
- "personalized: 1\n",
1542
- "treatment: 1\n",
1543
- "plans: 1\n",
1544
- "ai-driven: 3\n",
1545
- "fraudulent: 2\n",
1546
- "activities: 2\n",
1547
- "predict: 3\n",
1548
- "market: 1\n",
1549
- "enabling: 6\n",
1550
- "informed: 2\n",
1551
- "investment: 2\n",
1552
- "decisions: 6\n",
1553
- "automating: 2\n",
1554
- "cleaning: 4\n",
1555
- "preparation: 4\n",
1556
- "are: 5\n",
1557
- "crucial: 3\n",
1558
- "steps: 1\n",
1559
- "workflow: 1\n",
1560
- "accounting: 1\n",
1561
- "portion: 2\n",
1562
- "time: 2\n",
1563
- "spent: 1\n",
1564
- "project: 1\n",
1565
- "significantly: 2\n",
1566
- "improved: 2\n",
1567
- "these: 6\n",
1568
- "tasks: 3\n",
1569
- "through: 3\n",
1570
- "automation: 2\n",
1571
- "techniques: 4\n",
1572
- "natural: 4\n",
1573
- "language: 5\n",
1574
- "nlp: 6\n",
1575
- "computer: 2\n",
1576
- "vision: 2\n",
1577
- "automatically: 2\n",
1578
- "correct: 1\n",
1579
- "errors: 1\n",
1580
- "inconsistencies: 1\n",
1581
- "missing: 1\n",
1582
- "values: 2\n",
1583
- "example: 3\n",
1584
- "unstructured: 2\n",
1585
- "text: 3\n",
1586
- "relevant: 1\n",
1587
- "information: 1\n",
1588
- "transforming: 2\n",
1589
- "it: 3\n",
1590
- "into: 1\n",
1591
- "structured: 1\n",
1592
- "format: 1\n",
1593
- "suitable: 1\n",
1594
- "similarly: 1\n",
1595
- "images: 1\n",
1596
- "videos: 1\n",
1597
- "identifying: 2\n",
1598
- "objects: 1\n",
1599
- "meaningful: 1\n",
1600
- "features: 1\n",
1601
- "processes: 4\n",
1602
- "reduces: 1\n",
1603
- "manual: 1\n",
1604
- "effort: 1\n",
1605
- "required: 1\n",
1606
- "allowing: 2\n",
1607
- "scientists: 1\n",
1608
- "focus: 1\n",
1609
- "higher-level: 1\n",
1610
- "analytical: 1\n",
1611
- "advancing: 1\n",
1612
- "predictive: 6\n",
1613
- "analytics: 5\n",
1614
- "core: 1\n",
1615
- "component: 1\n",
1616
- "organizations: 3\n",
1617
- "make: 3\n",
1618
- "data-driven: 4\n",
1619
- "forecasting: 1\n",
1620
- "future: 1\n",
1621
- "outcomes: 3\n",
1622
- "advanced: 5\n",
1623
- "development: 1\n",
1624
- "sophisticated: 1\n",
1625
- "accurately: 1\n",
1626
- "model: 1\n",
1627
- "complex: 2\n",
1628
- "relationships: 1\n",
1629
- "within: 1\n",
1630
- "models: 4\n",
1631
- "regression: 1\n",
1632
- "decision: 3\n",
1633
- "trees: 1\n",
1634
- "neural: 1\n",
1635
- "networks: 1\n",
1636
- "based: 2\n",
1637
- "historical: 1\n",
1638
- "continuously: 1\n",
1639
- "learn: 1\n",
1640
- "improve: 1\n",
1641
- "new: 1\n",
1642
- "becomes: 1\n",
1643
- "available: 1\n",
1644
- "their: 2\n",
1645
- "over: 1\n",
1646
- "industries: 2\n",
1647
- "like: 3\n",
1648
- "retail: 1\n",
1649
- "powered: 2\n",
1650
- "optimize: 3\n",
1651
- "inventory: 2\n",
1652
- "management: 2\n",
1653
- "forecast: 1\n",
1654
- "customer: 2\n",
1655
- "demand: 2\n",
1656
- "personalize: 1\n",
1657
- "marketing: 2\n",
1658
- "strategies: 2\n",
1659
- "real-time: 7\n",
1660
- "many: 1\n",
1661
- "applications: 3\n",
1662
- "autonomous: 2\n",
1663
- "vehicles: 2\n",
1664
- "financial: 2\n",
1665
- "trading: 1\n",
1666
- "cybersecurity: 1\n",
1667
- "enabled: 2\n",
1668
- "leveraging: 2\n",
1669
- "stream: 2\n",
1670
- "edge: 3\n",
1671
- "computing: 2\n",
1672
- "involves: 1\n",
1673
- "immediate: 1\n",
1674
- "insights: 4\n",
1675
- "actions: 1\n",
1676
- "streaming: 1\n",
1677
- "sensors: 1\n",
1678
- "social: 2\n",
1679
- "media: 2\n",
1680
- "other: 1\n",
1681
- "sources: 1\n",
1682
- "anomalies: 1\n",
1683
- "triggering: 1\n",
1684
- "alerts: 1\n",
1685
- "essential: 2\n",
1686
- "making: 2\n",
1687
- "split-second: 1\n",
1688
- "ensure: 2\n",
1689
- "safety: 1\n",
1690
- "navigation: 1\n",
1691
- "brings: 1\n",
1692
- "closer: 1\n",
1693
- "source: 1\n",
1694
- "generation: 1\n",
1695
- "reducing: 2\n",
1696
- "latency: 1\n",
1697
- "bandwidth: 1\n",
1698
- "requirements: 1\n",
1699
- "deployed: 2\n",
1700
- "devices: 1\n",
1701
- "locally: 1\n",
1702
- "without: 1\n",
1703
- "relying: 1\n",
1704
- "centralized: 1\n",
1705
- "cloud: 1\n",
1706
- "servers: 1\n",
1707
- "scenarios: 2\n",
1708
- "quick: 1\n",
1709
- "response: 1\n",
1710
- "times: 1\n",
1711
- "critical: 1\n",
1712
- "industrial: 1\n",
1713
- "monitoring: 2\n",
1714
- "facilitating: 1\n",
1715
- "visualization: 6\n",
1716
- "vital: 1\n",
1717
- "aspect: 1\n",
1718
- "stakeholders: 1\n",
1719
- "understand: 1\n",
1720
- "graphical: 1\n",
1721
- "representations: 1\n",
1722
- "facilitated: 2\n",
1723
- "provide: 1\n",
1724
- "deeper: 1\n",
1725
- "intuitive: 1\n",
1726
- "understanding: 1\n",
1727
- "tools: 2\n",
1728
- "generate: 1\n",
1729
- "visualizations: 1\n",
1730
- "characteristics: 1\n",
1731
- "outliers: 1\n",
1732
- "also: 2\n",
1733
- "create: 1\n",
1734
- "interactive: 2\n",
1735
- "dashboards: 1\n",
1736
- "allow: 1\n",
1737
- "users: 1\n",
1738
- "explore: 1\n",
1739
- "dynamically: 1\n",
1740
- "adjusting: 1\n",
1741
- "parameters: 1\n",
1742
- "filters: 1\n",
1743
- "uncover: 1\n",
1744
- "hidden: 1\n",
1745
- "ai-powered: 2\n",
1746
- "platforms: 1\n",
1747
- "business: 1\n",
1748
- "present: 2\n",
1749
- "sales: 1\n",
1750
- "charts: 1\n",
1751
- "graphs: 1\n",
1752
- "executives: 1\n",
1753
- "quickly: 1\n",
1754
- "subfield: 1\n",
1755
- "interaction: 1\n",
1756
- "between: 2\n",
1757
- "computers: 1\n",
1758
- "constitutes: 1\n",
1759
- "today: 1\n",
1760
- "perform: 1\n",
1761
- "sentiment: 1\n",
1762
- "entity: 1\n",
1763
- "recognition: 1\n",
1764
- "summarization: 1\n",
1765
- "invaluable: 1\n",
1766
- "sentiments: 1\n",
1767
- "inform: 1\n",
1768
- "clinical: 1\n",
1769
- "notes: 1\n",
1770
- "research: 2\n",
1771
- "papers: 1\n",
1772
- "medical: 1\n",
1773
- "care: 1\n",
1774
- "improving: 1\n",
1775
- "fundamentally: 1\n",
1776
- "providing: 1\n",
1777
- "accurate: 1\n",
1778
- "actionable: 1\n",
1779
- "support: 2\n",
1780
- "systems: 3\n",
1781
- "evaluate: 1\n",
1782
- "multiple: 1\n",
1783
- "recommend: 1\n",
1784
- "optimal: 1\n",
1785
- "courses: 1\n",
1786
- "action: 1\n",
1787
- "supply: 1\n",
1788
- "chain: 1\n",
1789
- "levels: 1\n",
1790
- "fluctuations: 1\n",
1791
- "potential: 2\n",
1792
- "disruptions: 1\n",
1793
- "sector: 1\n",
1794
- "assess: 1\n",
1795
- "credit: 1\n",
1796
- "risks: 2\n",
1797
- "portfolios: 1\n",
1798
- "operational: 1\n",
1799
- "addressing: 2\n",
1800
- "ethical: 5\n",
1801
- "bias: 3\n",
1802
- "concerns: 3\n",
1803
- "while: 1\n",
1804
- "brought: 1\n",
1805
- "benefits: 1\n",
1806
- "raises: 1\n",
1807
- "important: 1\n",
1808
- "inadvertently: 1\n",
1809
- "perpetuate: 1\n",
1810
- "biases: 1\n",
1811
- "training: 2\n",
1812
- "unfair: 1\n",
1813
- "or: 1\n",
1814
- "discriminatory: 1\n",
1815
- "issues: 1\n",
1816
- "responsible: 1\n",
1817
- "use: 2\n",
1818
- "efforts: 1\n",
1819
- "mitigate: 1\n",
1820
- "include: 1\n",
1821
- "developing: 1\n",
1822
- "fairness-aware: 1\n",
1823
- "ensuring: 2\n",
1824
- "diverse: 1\n",
1825
- "representative: 1\n",
1826
- "implementing: 1\n",
1827
- "transparent: 1\n",
1828
- "explainable: 1\n",
1829
- "additionally: 1\n",
1830
- "guidelines: 1\n",
1831
- "regulations: 1\n",
1832
- "being: 1\n",
1833
- "established: 1\n",
1834
- "govern: 1\n",
1835
- "various: 2\n",
1836
- "designed: 1\n",
1837
- "manner: 1\n",
1838
- "respects: 1\n",
1839
- "rights: 1\n",
1840
- "societal: 1\n",
1841
- "conclusion: 1\n",
1842
- "profound: 1\n",
1843
- "far-reaching: 1\n",
1844
- "enhanced: 1\n",
1845
- "automated: 1\n",
1846
- "addressed: 1\n",
1847
- "continues: 1\n",
1848
- "evolve: 1\n",
1849
- "integration: 1\n",
1850
- "will: 1\n",
1851
- "drive: 1\n",
1852
- "further: 1\n",
1853
- "transformation: 1\n",
1854
- "across: 1\n",
1855
- "embracing: 1\n",
1856
- "synergy: 1\n",
1857
- "seeking: 1\n",
1858
- "harness: 1\n",
1859
- "full: 1\n",
1860
- "stay: 1\n",
1861
- "competitive: 1\n",
1862
- "an: 1\n",
1863
- "increasingly: 1\n",
1864
- "world: 1\n",
1865
- "Word Probability Analysis:\n",
1866
- "introduction: 0.0009\n",
1867
- "in: 0.0251\n",
1868
- "recent: 0.0009\n",
1869
- "years: 0.0009\n",
1870
- "the: 0.0214\n",
1871
- "convergence: 0.0009\n",
1872
- "of: 0.0186\n",
1873
- "artificial: 0.0019\n",
1874
- "intelligence: 0.0037\n",
1875
- "ai: 0.0270\n",
1876
- "and: 0.0576\n",
1877
- "data: 0.0530\n",
1878
- "science: 0.0130\n",
1879
- "has: 0.0102\n",
1880
- "revolutionized: 0.0009\n",
1881
- "numerous: 0.0019\n",
1882
- "fields: 0.0019\n",
1883
- "leading: 0.0019\n",
1884
- "to: 0.0195\n",
1885
- "significant: 0.0028\n",
1886
- "advancements: 0.0009\n",
1887
- "technology: 0.0009\n",
1888
- "healthcare: 0.0037\n",
1889
- "finance: 0.0019\n",
1890
- "more: 0.0046\n",
1891
- "with: 0.0028\n",
1892
- "its: 0.0019\n",
1893
- "ability: 0.0019\n",
1894
- "mimic: 0.0009\n",
1895
- "human: 0.0028\n",
1896
- "which: 0.0019\n",
1897
- "focuses: 0.0019\n",
1898
- "on: 0.0093\n",
1899
- "extracting: 0.0037\n",
1900
- "knowledge: 0.0009\n",
1901
- "from: 0.0019\n",
1902
- "together: 0.0009\n",
1903
- "form: 0.0009\n",
1904
- "a: 0.0084\n",
1905
- "powerful: 0.0009\n",
1906
- "combination: 0.0009\n",
1907
- "that: 0.0074\n",
1908
- "drives: 0.0009\n",
1909
- "innovation: 0.0019\n",
1910
- "efficiency: 0.0028\n",
1911
- "this: 0.0028\n",
1912
- "essay: 0.0009\n",
1913
- "explores: 0.0009\n",
1914
- "impact: 0.0019\n",
1915
- "highlighting: 0.0019\n",
1916
- "key: 0.0019\n",
1917
- "areas: 0.0009\n",
1918
- "where: 0.0037\n",
1919
- "transformed: 0.0037\n",
1920
- "processing: 0.0121\n",
1921
- "analysis: 0.0074\n",
1922
- "decision-making: 0.0037\n",
1923
- "enhancing: 0.0037\n",
1924
- "capabilities: 0.0037\n",
1925
- "one: 0.0009\n",
1926
- "primary: 0.0009\n",
1927
- "ways: 0.0009\n",
1928
- "impacted: 0.0009\n",
1929
- "is: 0.0112\n",
1930
- "by: 0.0084\n",
1931
- "traditional: 0.0009\n",
1932
- "methods: 0.0009\n",
1933
- "often: 0.0019\n",
1934
- "struggle: 0.0009\n",
1935
- "handle: 0.0009\n",
1936
- "vast: 0.0019\n",
1937
- "amounts: 0.0019\n",
1938
- "generated: 0.0028\n",
1939
- "today's: 0.0009\n",
1940
- "digital: 0.0009\n",
1941
- "age: 0.0009\n",
1942
- "algorithms: 0.0084\n",
1943
- "particularly: 0.0028\n",
1944
- "those: 0.0009\n",
1945
- "involving: 0.0009\n",
1946
- "machine: 0.0028\n",
1947
- "learning: 0.0037\n",
1948
- "ml: 0.0009\n",
1949
- "deep: 0.0009\n",
1950
- "can: 0.0214\n",
1951
- "process: 0.0037\n",
1952
- "analyze: 0.0046\n",
1953
- "massive: 0.0009\n",
1954
- "datasets: 0.0028\n",
1955
- "unprecedented: 0.0009\n",
1956
- "speed: 0.0009\n",
1957
- "accuracy: 0.0019\n",
1958
- "for: 0.0112\n",
1959
- "instance: 0.0009\n",
1960
- "identify: 0.0028\n",
1961
- "patterns: 0.0019\n",
1962
- "trends: 0.0046\n",
1963
- "large: 0.0009\n",
1964
- "would: 0.0009\n",
1965
- "be: 0.0009\n",
1966
- "impossible: 0.0009\n",
1967
- "humans: 0.0009\n",
1968
- "detect: 0.0028\n",
1969
- "manually: 0.0009\n",
1970
- "capability: 0.0019\n",
1971
- "valuable: 0.0028\n",
1972
- "such: 0.0056\n",
1973
- "as: 0.0084\n",
1974
- "analyzing: 0.0028\n",
1975
- "patient: 0.0019\n",
1976
- "lead: 0.0009\n",
1977
- "early: 0.0009\n",
1978
- "diagnosis: 0.0009\n",
1979
- "personalized: 0.0009\n",
1980
- "treatment: 0.0009\n",
1981
- "plans: 0.0009\n",
1982
- "ai-driven: 0.0028\n",
1983
- "fraudulent: 0.0019\n",
1984
- "activities: 0.0019\n",
1985
- "predict: 0.0028\n",
1986
- "market: 0.0009\n",
1987
- "enabling: 0.0056\n",
1988
- "informed: 0.0019\n",
1989
- "investment: 0.0019\n",
1990
- "decisions: 0.0056\n",
1991
- "automating: 0.0019\n",
1992
- "cleaning: 0.0037\n",
1993
- "preparation: 0.0037\n",
1994
- "are: 0.0046\n",
1995
- "crucial: 0.0028\n",
1996
- "steps: 0.0009\n",
1997
- "workflow: 0.0009\n",
1998
- "accounting: 0.0009\n",
1999
- "portion: 0.0019\n",
2000
- "time: 0.0019\n",
2001
- "spent: 0.0009\n",
2002
- "project: 0.0009\n",
2003
- "significantly: 0.0019\n",
2004
- "improved: 0.0019\n",
2005
- "these: 0.0056\n",
2006
- "tasks: 0.0028\n",
2007
- "through: 0.0028\n",
2008
- "automation: 0.0019\n",
2009
- "techniques: 0.0037\n",
2010
- "natural: 0.0037\n",
2011
- "language: 0.0046\n",
2012
- "nlp: 0.0056\n",
2013
- "computer: 0.0019\n",
2014
- "vision: 0.0019\n",
2015
- "automatically: 0.0019\n",
2016
- "correct: 0.0009\n",
2017
- "errors: 0.0009\n",
2018
- "inconsistencies: 0.0009\n",
2019
- "missing: 0.0009\n",
2020
- "values: 0.0019\n",
2021
- "example: 0.0028\n",
2022
- "unstructured: 0.0019\n",
2023
- "text: 0.0028\n",
2024
- "relevant: 0.0009\n",
2025
- "information: 0.0009\n",
2026
- "transforming: 0.0019\n",
2027
- "it: 0.0028\n",
2028
- "into: 0.0009\n",
2029
- "structured: 0.0009\n",
2030
- "format: 0.0009\n",
2031
- "suitable: 0.0009\n",
2032
- "similarly: 0.0009\n",
2033
- "images: 0.0009\n",
2034
- "videos: 0.0009\n",
2035
- "identifying: 0.0019\n",
2036
- "objects: 0.0009\n",
2037
- "meaningful: 0.0009\n",
2038
- "features: 0.0009\n",
2039
- "processes: 0.0037\n",
2040
- "reduces: 0.0009\n",
2041
- "manual: 0.0009\n",
2042
- "effort: 0.0009\n",
2043
- "required: 0.0009\n",
2044
- "allowing: 0.0019\n",
2045
- "scientists: 0.0009\n",
2046
- "focus: 0.0009\n",
2047
- "higher-level: 0.0009\n",
2048
- "analytical: 0.0009\n",
2049
- "advancing: 0.0009\n",
2050
- "predictive: 0.0056\n",
2051
- "analytics: 0.0046\n",
2052
- "core: 0.0009\n",
2053
- "component: 0.0009\n",
2054
- "organizations: 0.0028\n",
2055
- "make: 0.0028\n",
2056
- "data-driven: 0.0037\n",
2057
- "forecasting: 0.0009\n",
2058
- "future: 0.0009\n",
2059
- "outcomes: 0.0028\n",
2060
- "advanced: 0.0046\n",
2061
- "development: 0.0009\n",
2062
- "sophisticated: 0.0009\n",
2063
- "accurately: 0.0009\n",
2064
- "model: 0.0009\n",
2065
- "complex: 0.0019\n",
2066
- "relationships: 0.0009\n",
2067
- "within: 0.0009\n",
2068
- "models: 0.0037\n",
2069
- "regression: 0.0009\n",
2070
- "decision: 0.0028\n",
2071
- "trees: 0.0009\n",
2072
- "neural: 0.0009\n",
2073
- "networks: 0.0009\n",
2074
- "based: 0.0019\n",
2075
- "historical: 0.0009\n",
2076
- "continuously: 0.0009\n",
2077
- "learn: 0.0009\n",
2078
- "improve: 0.0009\n",
2079
- "new: 0.0009\n",
2080
- "becomes: 0.0009\n",
2081
- "available: 0.0009\n",
2082
- "their: 0.0019\n",
2083
- "over: 0.0009\n",
2084
- "industries: 0.0019\n",
2085
- "like: 0.0028\n",
2086
- "retail: 0.0009\n",
2087
- "powered: 0.0019\n",
2088
- "optimize: 0.0028\n",
2089
- "inventory: 0.0019\n",
2090
- "management: 0.0019\n",
2091
- "forecast: 0.0009\n",
2092
- "customer: 0.0019\n",
2093
- "demand: 0.0019\n",
2094
- "personalize: 0.0009\n",
2095
- "marketing: 0.0019\n",
2096
- "strategies: 0.0019\n",
2097
- "real-time: 0.0065\n",
2098
- "many: 0.0009\n",
2099
- "applications: 0.0028\n",
2100
- "autonomous: 0.0019\n",
2101
- "vehicles: 0.0019\n",
2102
- "financial: 0.0019\n",
2103
- "trading: 0.0009\n",
2104
- "cybersecurity: 0.0009\n",
2105
- "enabled: 0.0019\n",
2106
- "leveraging: 0.0019\n",
2107
- "stream: 0.0019\n",
2108
- "edge: 0.0028\n",
2109
- "computing: 0.0019\n",
2110
- "involves: 0.0009\n",
2111
- "immediate: 0.0009\n",
2112
- "insights: 0.0037\n",
2113
- "actions: 0.0009\n",
2114
- "streaming: 0.0009\n",
2115
- "sensors: 0.0009\n",
2116
- "social: 0.0019\n",
2117
- "media: 0.0019\n",
2118
- "other: 0.0009\n",
2119
- "sources: 0.0009\n",
2120
- "anomalies: 0.0009\n",
2121
- "triggering: 0.0009\n",
2122
- "alerts: 0.0009\n",
2123
- "essential: 0.0019\n",
2124
- "making: 0.0019\n",
2125
- "split-second: 0.0009\n",
2126
- "ensure: 0.0019\n",
2127
- "safety: 0.0009\n",
2128
- "navigation: 0.0009\n",
2129
- "brings: 0.0009\n",
2130
- "closer: 0.0009\n",
2131
- "source: 0.0009\n",
2132
- "generation: 0.0009\n",
2133
- "reducing: 0.0019\n",
2134
- "latency: 0.0009\n",
2135
- "bandwidth: 0.0009\n",
2136
- "requirements: 0.0009\n",
2137
- "deployed: 0.0019\n",
2138
- "devices: 0.0009\n",
2139
- "locally: 0.0009\n",
2140
- "without: 0.0009\n",
2141
- "relying: 0.0009\n",
2142
- "centralized: 0.0009\n",
2143
- "cloud: 0.0009\n",
2144
- "servers: 0.0009\n",
2145
- "scenarios: 0.0019\n",
2146
- "quick: 0.0009\n",
2147
- "response: 0.0009\n",
2148
- "times: 0.0009\n",
2149
- "critical: 0.0009\n",
2150
- "industrial: 0.0009\n",
2151
- "monitoring: 0.0019\n",
2152
- "facilitating: 0.0009\n",
2153
- "visualization: 0.0056\n",
2154
- "vital: 0.0009\n",
2155
- "aspect: 0.0009\n",
2156
- "stakeholders: 0.0009\n",
2157
- "understand: 0.0009\n",
2158
- "graphical: 0.0009\n",
2159
- "representations: 0.0009\n",
2160
- "facilitated: 0.0019\n",
2161
- "provide: 0.0009\n",
2162
- "deeper: 0.0009\n",
2163
- "intuitive: 0.0009\n",
2164
- "understanding: 0.0009\n",
2165
- "tools: 0.0019\n",
2166
- "generate: 0.0009\n",
2167
- "visualizations: 0.0009\n",
2168
- "characteristics: 0.0009\n",
2169
- "outliers: 0.0009\n",
2170
- "also: 0.0019\n",
2171
- "create: 0.0009\n",
2172
- "interactive: 0.0019\n",
2173
- "dashboards: 0.0009\n",
2174
- "allow: 0.0009\n",
2175
- "users: 0.0009\n",
2176
- "explore: 0.0009\n",
2177
- "dynamically: 0.0009\n",
2178
- "adjusting: 0.0009\n",
2179
- "parameters: 0.0009\n",
2180
- "filters: 0.0009\n",
2181
- "uncover: 0.0009\n",
2182
- "hidden: 0.0009\n",
2183
- "ai-powered: 0.0019\n",
2184
- "platforms: 0.0009\n",
2185
- "business: 0.0009\n",
2186
- "present: 0.0019\n",
2187
- "sales: 0.0009\n",
2188
- "charts: 0.0009\n",
2189
- "graphs: 0.0009\n",
2190
- "executives: 0.0009\n",
2191
- "quickly: 0.0009\n",
2192
- "subfield: 0.0009\n",
2193
- "interaction: 0.0009\n",
2194
- "between: 0.0019\n",
2195
- "computers: 0.0009\n",
2196
- "constitutes: 0.0009\n",
2197
- "today: 0.0009\n",
2198
- "perform: 0.0009\n",
2199
- "sentiment: 0.0009\n",
2200
- "entity: 0.0009\n",
2201
- "recognition: 0.0009\n",
2202
- "summarization: 0.0009\n",
2203
- "invaluable: 0.0009\n",
2204
- "sentiments: 0.0009\n",
2205
- "inform: 0.0009\n",
2206
- "clinical: 0.0009\n",
2207
- "notes: 0.0009\n",
2208
- "research: 0.0019\n",
2209
- "papers: 0.0009\n",
2210
- "medical: 0.0009\n",
2211
- "care: 0.0009\n",
2212
- "improving: 0.0009\n",
2213
- "fundamentally: 0.0009\n",
2214
- "providing: 0.0009\n",
2215
- "accurate: 0.0009\n",
2216
- "actionable: 0.0009\n",
2217
- "support: 0.0019\n",
2218
- "systems: 0.0028\n",
2219
- "evaluate: 0.0009\n",
2220
- "multiple: 0.0009\n",
2221
- "recommend: 0.0009\n",
2222
- "optimal: 0.0009\n",
2223
- "courses: 0.0009\n",
2224
- "action: 0.0009\n",
2225
- "supply: 0.0009\n",
2226
- "chain: 0.0009\n",
2227
- "levels: 0.0009\n",
2228
- "fluctuations: 0.0009\n",
2229
- "potential: 0.0019\n",
2230
- "disruptions: 0.0009\n",
2231
- "sector: 0.0009\n",
2232
- "assess: 0.0009\n",
2233
- "credit: 0.0009\n",
2234
- "risks: 0.0019\n",
2235
- "portfolios: 0.0009\n",
2236
- "operational: 0.0009\n",
2237
- "addressing: 0.0019\n",
2238
- "ethical: 0.0046\n",
2239
- "bias: 0.0028\n",
2240
- "concerns: 0.0028\n",
2241
- "while: 0.0009\n",
2242
- "brought: 0.0009\n",
2243
- "benefits: 0.0009\n",
2244
- "raises: 0.0009\n",
2245
- "important: 0.0009\n",
2246
- "inadvertently: 0.0009\n",
2247
- "perpetuate: 0.0009\n",
2248
- "biases: 0.0009\n",
2249
- "training: 0.0019\n",
2250
- "unfair: 0.0009\n",
2251
- "or: 0.0009\n",
2252
- "discriminatory: 0.0009\n",
2253
- "issues: 0.0009\n",
2254
- "responsible: 0.0009\n",
2255
- "use: 0.0019\n",
2256
- "efforts: 0.0009\n",
2257
- "mitigate: 0.0009\n",
2258
- "include: 0.0009\n",
2259
- "developing: 0.0009\n",
2260
- "fairness-aware: 0.0009\n",
2261
- "ensuring: 0.0019\n",
2262
- "diverse: 0.0009\n",
2263
- "representative: 0.0009\n",
2264
- "implementing: 0.0009\n",
2265
- "transparent: 0.0009\n",
2266
- "explainable: 0.0009\n",
2267
- "additionally: 0.0009\n",
2268
- "guidelines: 0.0009\n",
2269
- "regulations: 0.0009\n",
2270
- "being: 0.0009\n",
2271
- "established: 0.0009\n",
2272
- "govern: 0.0009\n",
2273
- "various: 0.0019\n",
2274
- "designed: 0.0009\n",
2275
- "manner: 0.0009\n",
2276
- "respects: 0.0009\n",
2277
- "rights: 0.0009\n",
2278
- "societal: 0.0009\n",
2279
- "conclusion: 0.0009\n",
2280
- "profound: 0.0009\n",
2281
- "far-reaching: 0.0009\n",
2282
- "enhanced: 0.0009\n",
2283
- "automated: 0.0009\n",
2284
- "addressed: 0.0009\n",
2285
- "continues: 0.0009\n",
2286
- "evolve: 0.0009\n",
2287
- "integration: 0.0009\n",
2288
- "will: 0.0009\n",
2289
- "drive: 0.0009\n",
2290
- "further: 0.0009\n",
2291
- "transformation: 0.0009\n",
2292
- "across: 0.0009\n",
2293
- "embracing: 0.0009\n",
2294
- "synergy: 0.0009\n",
2295
- "seeking: 0.0009\n",
2296
- "harness: 0.0009\n",
2297
- "full: 0.0009\n",
2298
- "stay: 0.0009\n",
2299
- "competitive: 0.0009\n",
2300
- "an: 0.0009\n",
2301
- "increasingly: 0.0009\n",
2302
- "world: 0.0009\n"
2303
- ]
2304
- },
2305
- {
2306
- "data": {
2307
- "image/png": "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",
2308
- "text/plain": [
2309
- "<Figure size 1200x800 with 1 Axes>"
2310
- ]
2311
- },
2312
- "metadata": {},
2313
- "output_type": "display_data"
2314
- }
2315
- ],
2316
- "source": [
2317
- "# Function to read the CSV file and return the text content\n",
2318
- "def read_csv_file(file_path):\n",
2319
- " essay_text = \"\"\n",
2320
- " with open(file_path, 'r') as file:\n",
2321
- " for line in file:\n",
2322
- " # Remove newline characters and quotes, then append to essay_text\n",
2323
- " essay_text += line.strip().replace('\"', '') + \" \"\n",
2324
- " return essay_text\n",
2325
- "\n",
2326
- "# Function to tokenize the text into words\n",
2327
- "def tokenize(text):\n",
2328
- " words = text.split()\n",
2329
- " return [word.strip(\".,!?\\\"'()[]{}:;\") for word in words]\n",
2330
- "\n",
2331
- "# Function to perform frequency analysis\n",
2332
- "def frequency_analysis(words):\n",
2333
- " frequency = {}\n",
2334
- " for word in words:\n",
2335
- " if word.lower() in frequency:\n",
2336
- " frequency[word.lower()] += 1\n",
2337
- " else:\n",
2338
- " frequency[word.lower()] = 1\n",
2339
- " return frequency\n",
2340
- "\n",
2341
- "# Function to calculate word probabilities\n",
2342
- "def calculate_probabilities(frequency):\n",
2343
- " total_words = sum(frequency.values())\n",
2344
- " probabilities = {word: freq / total_words for word, freq in frequency.items()}\n",
2345
- " return probabilities\n",
2346
- "\n",
2347
- "# Load the essay text from the CSV file\n",
2348
- "essay_text = read_csv_file('E:/126156048/csv1.csv')\n",
2349
- "\n",
2350
- "# Tokenize the text into words\n",
2351
- "words = tokenize(essay_text)\n",
2352
- "\n",
2353
- "# Perform frequency analysis\n",
2354
- "word_freq = frequency_analysis(words)\n",
2355
- "\n",
2356
- "# Calculate word probabilities\n",
2357
- "word_prob = calculate_probabilities(word_freq)\n",
2358
- "\n",
2359
- "# Find the number of unique words\n",
2360
- "num_unique_words = len(word_freq)\n",
2361
- "\n",
2362
- "# Display the number of unique words\n",
2363
- "print(f\"Number of unique words: {num_unique_words}\")\n",
2364
- "\n",
2365
- "# Display the frequency of each word\n",
2366
- "print(\"Word Frequency Analysis:\")\n",
2367
- "for word, freq in word_freq.items():\n",
2368
- " print(f\"{word}: {freq}\")\n",
2369
- "\n",
2370
- "# Display the probability of each word\n",
2371
- "print(\"Word Probability Analysis:\")\n",
2372
- "for word, prob in word_prob.items():\n",
2373
- " print(f\"{word}: {prob:.4f}\")\n",
2374
- "\n",
2375
- "# Prepare data for plotting\n",
2376
- "import matplotlib.pyplot as plt\n",
2377
- "\n",
2378
- "# Sort words by probability and get the top 10\n",
2379
- "sorted_word_prob = sorted(word_prob.items(), key=lambda x: x[1], reverse=True)\n",
2380
- "top_words = sorted_word_prob[:10]\n",
2381
- "words, probabilities = zip(*top_words)\n",
2382
- "\n",
2383
- "# Plotting\n",
2384
- "plt.figure(figsize=(12, 8))\n",
2385
- "plt.bar(words, probabilities, color='skyblue')\n",
2386
- "plt.xlabel('Words')\n",
2387
- "plt.ylabel('Probability')\n",
2388
- "plt.title('Top 10 Words by Probability')\n",
2389
- "plt.xticks(rotation=45, ha='right')\n",
2390
- "plt.tight_layout() # Adjust layout to prevent clipping of labels\n",
2391
- "plt.show()\n"
2392
- ]
2393
- },
2394
- {
2395
- "cell_type": "code",
2396
- "execution_count": 82,
2397
- "id": "731e7a34-1e0b-443e-9851-2a175d9be23a",
2398
- "metadata": {},
2399
- "outputs": [
2400
- {
2401
- "data": {
2402
- "image/png": "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",
2403
- "text/plain": [
2404
- "<Figure size 1000x600 with 1 Axes>"
2405
- ]
2406
- },
2407
- "metadata": {},
2408
- "output_type": "display_data"
2409
- }
2410
- ],
2411
- "source": [
2412
- "# Prepare data for plotting\n",
2413
- "# Sort words by frequency and get the top 10\n",
2414
- "sorted_word_freq = sorted(word_freq.items(), key=lambda x: x[1], reverse=True)\n",
2415
- "top_words = sorted_word_freq[:10]\n",
2416
- "words, frequencies = zip(*top_words)\n",
2417
- "\n",
2418
- "# Plotting\n",
2419
- "plt.figure(figsize=(10, 6))\n",
2420
- "plt.bar(words, frequencies, color='skyblue')\n",
2421
- "plt.xlabel('Words')\n",
2422
- "plt.ylabel('Frequency')\n",
2423
- "plt.title('Top 10 Words by Frequency')\n",
2424
- "plt.xticks(rotation=45, ha='right')\n",
2425
- "plt.tight_layout() # Adjust layout to prevent clipping of labels\n",
2426
- "plt.show()\n"
2427
- ]
2428
- },
2429
- {
2430
- "cell_type": "code",
2431
- "execution_count": 88,
2432
- "id": "d1b37a65-66ce-470a-9742-60b0c3d6c371",
2433
- "metadata": {},
2434
- "outputs": [],
2435
- "source": [
2436
- "# Define a list of common stop words\n",
2437
- "stop_words = set([\n",
2438
- " 'the', 'is', 'in' ,'In', 'and', 'to', 'of', 'for', 'on', 'with', 'a', 'an', 'it', 'that', 'as', 'by', 'at', 'or', 'from', 'was', 'which', 'are', 'be', 'will', 'has', 'have', 'had', 'not', 'you', 'this', 'but', 'we', 'they', 'can', 'if', 'has', 'more', 'other', 'than', 'so', 'up', 'out', 'over', 'under', 'into', 'its', 'been', 'are', 'all', 'some', 'would', 'also', 'such', 'their', 'our', 'about', 'these', 'those', 'where', 'when', 'why', 'how', 'each', 'both', 'few', 'many', 'most', 'much', 'only', 'most', 'then', 'here', 'there'\n",
2439
- "])"
2440
- ]
2441
- },
2442
- {
2443
- "cell_type": "code",
2444
- "execution_count": 89,
2445
- "id": "a188a071-fd04-4db7-be97-75b7644db4c2",
2446
- "metadata": {},
2447
- "outputs": [],
2448
- "source": [
2449
- "# Function to perform frequency analysis\n",
2450
- "def frequency_analysis(words, stop_words):\n",
2451
- " frequency = {}\n",
2452
- " for word in words:\n",
2453
- " if word not in stop_words and word != '':\n",
2454
- " if word in frequency:\n",
2455
- " frequency[word] += 1\n",
2456
- " else:\n",
2457
- " frequency[word] = 1\n",
2458
- " return frequency"
2459
- ]
2460
- },
2461
- {
2462
- "cell_type": "code",
2463
- "execution_count": 90,
2464
- "id": "de655548-6dc7-4698-9a67-03a56477478f",
2465
- "metadata": {},
2466
- "outputs": [],
2467
- "source": [
2468
- "# Tokenize the text into words\n",
2469
- "words = tokenize(essay_text)\n",
2470
- "\n",
2471
- "# Perform frequency analysis excluding stop words\n",
2472
- "word_freq = frequency_analysis(words, stop_words)\n",
2473
- "\n",
2474
- "# Find the number of unique words\n",
2475
- "num_unique_words = len(word_freq)"
2476
- ]
2477
- },
2478
- {
2479
- "cell_type": "code",
2480
- "execution_count": 91,
2481
- "id": "9fd01b99-e7dd-4fb9-99e9-c418d9a1aa2c",
2482
- "metadata": {},
2483
- "outputs": [
2484
- {
2485
- "name": "stdout",
2486
- "output_type": "stream",
2487
- "text": [
2488
- "Number of unique words: 433\n"
2489
- ]
2490
- }
2491
- ],
2492
- "source": [
2493
- "# Display the number of unique words\n",
2494
- "print(f\"Number of unique words: {num_unique_words}\")"
2495
- ]
2496
- },
2497
- {
2498
- "cell_type": "code",
2499
- "execution_count": 92,
2500
- "id": "a23851bf-5021-439b-9d87-4bdc066c602a",
2501
- "metadata": {},
2502
- "outputs": [
2503
- {
2504
- "data": {
2505
- "image/png": "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",
2506
- "text/plain": [
2507
- "<Figure size 1000x600 with 1 Axes>"
2508
- ]
2509
- },
2510
- "metadata": {},
2511
- "output_type": "display_data"
2512
- }
2513
- ],
2514
- "source": [
2515
- "# Prepare data for plotting\n",
2516
- "# Sort words by frequency and get the top 10\n",
2517
- "sorted_word_freq = sorted(word_freq.items(), key=lambda x: x[1], reverse=True)\n",
2518
- "top_words = sorted_word_freq[:10]\n",
2519
- "words, frequencies = zip(*top_words)\n",
2520
- "\n",
2521
- "# Plotting\n",
2522
- "plt.figure(figsize=(10, 6))\n",
2523
- "plt.bar(words, frequencies, color='skyblue')\n",
2524
- "plt.xlabel('Words')\n",
2525
- "plt.ylabel('Frequency')\n",
2526
- "plt.title('Top 10 Words by Frequency (Excluding Stop Words)')\n",
2527
- "plt.xticks(rotation=45, ha='right')\n",
2528
- "plt.tight_layout() # Adjust layout to prevent clipping of labels\n",
2529
- "plt.show()"
2530
- ]
2531
- },
2532
- {
2533
- "cell_type": "code",
2534
- "execution_count": 93,
2535
- "id": "7b080c48-57c8-4020-a51e-88ffeb1003da",
2536
- "metadata": {},
2537
- "outputs": [
2538
- {
2539
- "name": "stdout",
2540
- "output_type": "stream",
2541
- "text": [
2542
- "Word Frequency Analysis:\n",
2543
- "Introduction: 1\n",
2544
- "recent: 1\n",
2545
- "years: 1\n",
2546
- "convergence: 1\n",
2547
- "artificial: 2\n",
2548
- "intelligence: 4\n",
2549
- "AI: 29\n",
2550
- "data: 51\n",
2551
- "science: 14\n",
2552
- "revolutionized: 1\n",
2553
- "numerous: 2\n",
2554
- "fields: 2\n",
2555
- "leading: 2\n",
2556
- "significant: 3\n",
2557
- "advancements: 1\n",
2558
- "technology: 1\n",
2559
- "healthcare: 4\n",
2560
- "finance: 2\n",
2561
- "ability: 2\n",
2562
- "mimic: 1\n",
2563
- "human: 3\n",
2564
- "focuses: 2\n",
2565
- "extracting: 4\n",
2566
- "knowledge: 1\n",
2567
- "together: 1\n",
2568
- "form: 1\n",
2569
- "powerful: 1\n",
2570
- "combination: 1\n",
2571
- "drives: 1\n",
2572
- "innovation: 2\n",
2573
- "efficiency: 3\n",
2574
- "This: 3\n",
2575
- "essay: 1\n",
2576
- "explores: 1\n",
2577
- "impact: 2\n",
2578
- "highlighting: 2\n",
2579
- "key: 2\n",
2580
- "areas: 1\n",
2581
- "transformed: 4\n",
2582
- "processing: 11\n",
2583
- "analysis: 7\n",
2584
- "decision-making: 3\n",
2585
- "Enhancing: 1\n",
2586
- "Data: 6\n",
2587
- "Processing: 2\n",
2588
- "Capabilities: 1\n",
2589
- "One: 1\n",
2590
- "primary: 1\n",
2591
- "ways: 1\n",
2592
- "impacted: 1\n",
2593
- "enhancing: 3\n",
2594
- "capabilities: 3\n",
2595
- "Traditional: 1\n",
2596
- "methods: 1\n",
2597
- "often: 2\n",
2598
- "struggle: 1\n",
2599
- "handle: 1\n",
2600
- "vast: 2\n",
2601
- "amounts: 2\n",
2602
- "generated: 3\n",
2603
- "today's: 1\n",
2604
- "digital: 1\n",
2605
- "age: 1\n",
2606
- "algorithms: 9\n",
2607
- "particularly: 3\n",
2608
- "involving: 1\n",
2609
- "machine: 1\n",
2610
- "learning: 4\n",
2611
- "ML: 1\n",
2612
- "deep: 1\n",
2613
- "process: 4\n",
2614
- "analyze: 5\n",
2615
- "massive: 1\n",
2616
- "datasets: 3\n",
2617
- "unprecedented: 1\n",
2618
- "speed: 1\n",
2619
- "accuracy: 2\n",
2620
- "Machine: 2\n",
2621
- "instance: 1\n",
2622
- "identify: 3\n",
2623
- "patterns: 2\n",
2624
- "trends: 5\n",
2625
- "large: 1\n",
2626
- "impossible: 1\n",
2627
- "humans: 1\n",
2628
- "detect: 3\n",
2629
- "manually: 1\n",
2630
- "capability: 2\n",
2631
- "valuable: 3\n",
2632
- "analyzing: 3\n",
2633
- "patient: 2\n",
2634
- "lead: 1\n",
2635
- "early: 1\n",
2636
- "diagnosis: 1\n",
2637
- "personalized: 1\n",
2638
- "treatment: 1\n",
2639
- "plans: 1\n",
2640
- "AI-driven: 3\n",
2641
- "fraudulent: 2\n",
2642
- "activities: 2\n",
2643
- "predict: 3\n",
2644
- "market: 1\n",
2645
- "enabling: 5\n",
2646
- "informed: 2\n",
2647
- "investment: 2\n",
2648
- "decisions: 6\n",
2649
- "Automating: 1\n",
2650
- "Cleaning: 1\n",
2651
- "Preparation: 1\n",
2652
- "cleaning: 3\n",
2653
- "preparation: 3\n",
2654
- "crucial: 3\n",
2655
- "steps: 1\n",
2656
- "workflow: 1\n",
2657
- "accounting: 1\n",
2658
- "portion: 2\n",
2659
- "time: 2\n",
2660
- "spent: 1\n",
2661
- "project: 1\n",
2662
- "significantly: 2\n",
2663
- "improved: 2\n",
2664
- "tasks: 3\n",
2665
- "through: 3\n",
2666
- "automation: 2\n",
2667
- "Techniques: 1\n",
2668
- "natural: 2\n",
2669
- "language: 4\n",
2670
- "NLP: 6\n",
2671
- "computer: 2\n",
2672
- "vision: 2\n",
2673
- "automatically: 2\n",
2674
- "correct: 1\n",
2675
- "errors: 1\n",
2676
- "inconsistencies: 1\n",
2677
- "missing: 1\n",
2678
- "values: 2\n",
2679
- "For: 2\n",
2680
- "example: 3\n",
2681
- "unstructured: 2\n",
2682
- "text: 3\n",
2683
- "relevant: 1\n",
2684
- "information: 1\n",
2685
- "transforming: 1\n",
2686
- "structured: 1\n",
2687
- "format: 1\n",
2688
- "suitable: 1\n",
2689
- "Similarly: 1\n",
2690
- "techniques: 3\n",
2691
- "images: 1\n",
2692
- "videos: 1\n",
2693
- "identifying: 2\n",
2694
- "objects: 1\n",
2695
- "meaningful: 1\n",
2696
- "features: 1\n",
2697
- "By: 2\n",
2698
- "automating: 1\n",
2699
- "processes: 3\n",
2700
- "reduces: 1\n",
2701
- "manual: 1\n",
2702
- "effort: 1\n",
2703
- "required: 1\n",
2704
- "allowing: 2\n",
2705
- "scientists: 1\n",
2706
- "focus: 1\n",
2707
- "higher-level: 1\n",
2708
- "analytical: 1\n",
2709
- "Advancing: 1\n",
2710
- "Predictive: 2\n",
2711
- "Analytics: 1\n",
2712
- "analytics: 4\n",
2713
- "core: 1\n",
2714
- "component: 1\n",
2715
- "organizations: 3\n",
2716
- "make: 3\n",
2717
- "data-driven: 4\n",
2718
- "forecasting: 1\n",
2719
- "future: 1\n",
2720
- "outcomes: 3\n",
2721
- "advanced: 4\n",
2722
- "predictive: 4\n",
2723
- "development: 1\n",
2724
- "sophisticated: 1\n",
2725
- "accurately: 1\n",
2726
- "model: 1\n",
2727
- "complex: 2\n",
2728
- "relationships: 1\n",
2729
- "within: 1\n",
2730
- "models: 4\n",
2731
- "regression: 1\n",
2732
- "decision: 2\n",
2733
- "trees: 1\n",
2734
- "neural: 1\n",
2735
- "networks: 1\n",
2736
- "based: 2\n",
2737
- "historical: 1\n",
2738
- "These: 3\n",
2739
- "continuously: 1\n",
2740
- "learn: 1\n",
2741
- "improve: 1\n",
2742
- "new: 1\n",
2743
- "becomes: 1\n",
2744
- "available: 1\n",
2745
- "industries: 2\n",
2746
- "like: 3\n",
2747
- "retail: 1\n",
2748
- "powered: 2\n",
2749
- "optimize: 3\n",
2750
- "inventory: 2\n",
2751
- "management: 2\n",
2752
- "forecast: 1\n",
2753
- "customer: 2\n",
2754
- "demand: 2\n",
2755
- "personalize: 1\n",
2756
- "marketing: 2\n",
2757
- "strategies: 2\n",
2758
- "Enabling: 1\n",
2759
- "Real-Time: 1\n",
2760
- "Analysis: 1\n",
2761
- "The: 2\n",
2762
- "real-time: 6\n",
2763
- "applications: 3\n",
2764
- "autonomous: 2\n",
2765
- "vehicles: 2\n",
2766
- "financial: 2\n",
2767
- "trading: 1\n",
2768
- "cybersecurity: 1\n",
2769
- "enabled: 2\n",
2770
- "leveraging: 2\n",
2771
- "stream: 1\n",
2772
- "edge: 2\n",
2773
- "computing: 2\n",
2774
- "Stream: 1\n",
2775
- "involves: 1\n",
2776
- "immediate: 1\n",
2777
- "insights: 4\n",
2778
- "actions: 1\n",
2779
- "streaming: 1\n",
2780
- "sensors: 1\n",
2781
- "social: 2\n",
2782
- "media: 2\n",
2783
- "sources: 1\n",
2784
- "anomalies: 1\n",
2785
- "triggering: 1\n",
2786
- "alerts: 1\n",
2787
- "essential: 2\n",
2788
- "making: 2\n",
2789
- "split-second: 1\n",
2790
- "ensure: 2\n",
2791
- "safety: 1\n",
2792
- "navigation: 1\n",
2793
- "Edge: 1\n",
2794
- "brings: 1\n",
2795
- "closer: 1\n",
2796
- "source: 1\n",
2797
- "generation: 1\n",
2798
- "reducing: 2\n",
2799
- "latency: 1\n",
2800
- "bandwidth: 1\n",
2801
- "requirements: 1\n",
2802
- "deployed: 2\n",
2803
- "devices: 1\n",
2804
- "locally: 1\n",
2805
- "without: 1\n",
2806
- "relying: 1\n",
2807
- "centralized: 1\n",
2808
- "cloud: 1\n",
2809
- "servers: 1\n",
2810
- "scenarios: 2\n",
2811
- "quick: 1\n",
2812
- "response: 1\n",
2813
- "times: 1\n",
2814
- "critical: 1\n",
2815
- "industrial: 1\n",
2816
- "monitoring: 2\n",
2817
- "Facilitating: 1\n",
2818
- "Advanced: 1\n",
2819
- "Visualization: 1\n",
2820
- "visualization: 5\n",
2821
- "vital: 1\n",
2822
- "aspect: 1\n",
2823
- "stakeholders: 1\n",
2824
- "understand: 1\n",
2825
- "graphical: 1\n",
2826
- "representations: 1\n",
2827
- "facilitated: 2\n",
2828
- "provide: 1\n",
2829
- "deeper: 1\n",
2830
- "intuitive: 1\n",
2831
- "understanding: 1\n",
2832
- "tools: 2\n",
2833
- "generate: 1\n",
2834
- "visualizations: 1\n",
2835
- "characteristics: 1\n",
2836
- "outliers: 1\n",
2837
- "create: 1\n",
2838
- "interactive: 2\n",
2839
- "dashboards: 1\n",
2840
- "allow: 1\n",
2841
- "users: 1\n",
2842
- "explore: 1\n",
2843
- "dynamically: 1\n",
2844
- "adjusting: 1\n",
2845
- "parameters: 1\n",
2846
- "filters: 1\n",
2847
- "uncover: 1\n",
2848
- "hidden: 1\n",
2849
- "AI-powered: 2\n",
2850
- "platforms: 1\n",
2851
- "business: 1\n",
2852
- "present: 2\n",
2853
- "sales: 1\n",
2854
- "charts: 1\n",
2855
- "graphs: 1\n",
2856
- "executives: 1\n",
2857
- "quickly: 1\n",
2858
- "Transforming: 1\n",
2859
- "Natural: 2\n",
2860
- "Language: 1\n",
2861
- "subfield: 1\n",
2862
- "interaction: 1\n",
2863
- "between: 2\n",
2864
- "computers: 1\n",
2865
- "constitutes: 1\n",
2866
- "today: 1\n",
2867
- "perform: 1\n",
2868
- "sentiment: 1\n",
2869
- "entity: 1\n",
2870
- "recognition: 1\n",
2871
- "summarization: 1\n",
2872
- "invaluable: 1\n",
2873
- "sentiments: 1\n",
2874
- "inform: 1\n",
2875
- "clinical: 1\n",
2876
- "notes: 1\n",
2877
- "research: 2\n",
2878
- "papers: 1\n",
2879
- "medical: 1\n",
2880
- "care: 1\n",
2881
- "Improving: 1\n",
2882
- "Decision-Making: 1\n",
2883
- "Processes: 1\n",
2884
- "fundamentally: 1\n",
2885
- "providing: 1\n",
2886
- "accurate: 1\n",
2887
- "actionable: 1\n",
2888
- "Decision: 1\n",
2889
- "support: 2\n",
2890
- "systems: 3\n",
2891
- "evaluate: 1\n",
2892
- "multiple: 1\n",
2893
- "recommend: 1\n",
2894
- "optimal: 1\n",
2895
- "courses: 1\n",
2896
- "action: 1\n",
2897
- "supply: 1\n",
2898
- "chain: 1\n",
2899
- "levels: 1\n",
2900
- "fluctuations: 1\n",
2901
- "potential: 2\n",
2902
- "disruptions: 1\n",
2903
- "sector: 1\n",
2904
- "assess: 1\n",
2905
- "credit: 1\n",
2906
- "risks: 2\n",
2907
- "portfolios: 1\n",
2908
- "operational: 1\n",
2909
- "Addressing: 2\n",
2910
- "Ethical: 1\n",
2911
- "Bias: 1\n",
2912
- "Concerns: 1\n",
2913
- "While: 1\n",
2914
- "brought: 1\n",
2915
- "benefits: 1\n",
2916
- "raises: 1\n",
2917
- "important: 1\n",
2918
- "ethical: 4\n",
2919
- "bias: 2\n",
2920
- "concerns: 2\n",
2921
- "inadvertently: 1\n",
2922
- "perpetuate: 1\n",
2923
- "biases: 1\n",
2924
- "training: 2\n",
2925
- "unfair: 1\n",
2926
- "discriminatory: 1\n",
2927
- "issues: 1\n",
2928
- "responsible: 1\n",
2929
- "use: 2\n",
2930
- "Efforts: 1\n",
2931
- "mitigate: 1\n",
2932
- "include: 1\n",
2933
- "developing: 1\n",
2934
- "fairness-aware: 1\n",
2935
- "ensuring: 2\n",
2936
- "diverse: 1\n",
2937
- "representative: 1\n",
2938
- "implementing: 1\n",
2939
- "transparent: 1\n",
2940
- "explainable: 1\n",
2941
- "Additionally: 1\n",
2942
- "guidelines: 1\n",
2943
- "regulations: 1\n",
2944
- "being: 1\n",
2945
- "established: 1\n",
2946
- "govern: 1\n",
2947
- "various: 2\n",
2948
- "designed: 1\n",
2949
- "manner: 1\n",
2950
- "respects: 1\n",
2951
- "rights: 1\n",
2952
- "societal: 1\n",
2953
- "Conclusion: 1\n",
2954
- "profound: 1\n",
2955
- "far-reaching: 1\n",
2956
- "enhanced: 1\n",
2957
- "automated: 1\n",
2958
- "addressed: 1\n",
2959
- "As: 1\n",
2960
- "continues: 1\n",
2961
- "evolve: 1\n",
2962
- "integration: 1\n",
2963
- "drive: 1\n",
2964
- "further: 1\n",
2965
- "transformation: 1\n",
2966
- "across: 1\n",
2967
- "Embracing: 1\n",
2968
- "synergy: 1\n",
2969
- "seeking: 1\n",
2970
- "harness: 1\n",
2971
- "full: 1\n",
2972
- "stay: 1\n",
2973
- "competitive: 1\n",
2974
- "increasingly: 1\n",
2975
- "world: 1\n"
2976
- ]
2977
- }
2978
- ],
2979
- "source": [
2980
- "# Display the frequency of each word\n",
2981
- "print(\"Word Frequency Analysis:\")\n",
2982
- "for word, freq in word_freq.items():\n",
2983
- " print(f\"{word}: {freq}\")"
2984
- ]
2985
- }
2986
- ],
2987
- "metadata": {
2988
- "kernelspec": {
2989
- "display_name": "Python 3 (ipykernel)",
2990
- "language": "python",
2991
- "name": "python3"
2992
- },
2993
- "language_info": {
2994
- "codemirror_mode": {
2995
- "name": "ipython",
2996
- "version": 3
2997
- },
2998
- "file_extension": ".py",
2999
- "mimetype": "text/x-python",
3000
- "name": "python",
3001
- "nbconvert_exporter": "python",
3002
- "pygments_lexer": "ipython3",
3003
- "version": "3.11.7"
3004
- }
3005
- },
3006
- "nbformat": 4,
3007
- "nbformat_minor": 5
3008
- }