noshot 2.0.0__py3-none-any.whl → 4.0.0__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 (43) hide show
  1. noshot/data/ML TS XAI/ML/ML Lab CIA 2 (I Found Only This Check)/Copy_of_Pistachio_csv.ipynb +269 -0
  2. noshot/data/ML TS XAI/ML/ML Lab CIA 2 (I Found Only This Check)/weatherAUS.ipynb +155 -0
  3. noshot/data/ML TS XAI/ML/Main/1. EDA-PCA (Balance Scale Dataset).ipynb +139 -0
  4. noshot/data/ML TS XAI/ML/Main/1. EDA-PCA (Rice Dataset).ipynb +181 -0
  5. noshot/data/ML TS XAI/ML/Main/10. HMM Veterbi.ipynb +228 -0
  6. noshot/data/ML TS XAI/ML/Main/2. KNN (Balance Scale Dataset).ipynb +117 -0
  7. noshot/data/ML TS XAI/ML/Main/2. KNN (Iris Dataset).ipynb +165 -0
  8. noshot/data/ML TS XAI/ML/Main/2. KNN (Sobar-72 Dataset).ipynb +251 -0
  9. noshot/data/ML TS XAI/ML/Main/3. LDA (Balance Scale Dataset).ipynb +78 -0
  10. noshot/data/ML TS XAI/ML/Main/3. LDA (NPHA Doctor Visits Dataset).ipynb +114 -0
  11. noshot/data/ML TS XAI/ML/Main/4. Linear Regression (Machine Dataset).ipynb +115 -0
  12. noshot/data/ML TS XAI/ML/Main/4. Linear Regression (Real Estate Dataset).ipynb +159 -0
  13. noshot/data/ML TS XAI/ML/Main/5. Logistic Regression (Magic04 Dataset).ipynb +200 -0
  14. noshot/data/ML TS XAI/ML/Main/5. Logistic Regression (Wine Dataset).ipynb +112 -0
  15. noshot/data/ML TS XAI/ML/Main/6. Naive Bayes Classifier (Agaricus Lepiota Dataset).ipynb +153 -0
  16. noshot/data/ML TS XAI/ML/Main/6. Naive Bayes Classifier (Wine Dataset).ipynb +89 -0
  17. noshot/data/ML TS XAI/ML/Main/7. SVM (Rice Dataset).ipynb +208 -0
  18. noshot/data/ML TS XAI/ML/Main/8. FeedForward NN (Sobar72 Dataset).ipynb +260 -0
  19. noshot/data/ML TS XAI/ML/Main/9. CNN (Cifar10 Dataset).ipynb +238 -0
  20. noshot/data/ML TS XAI/ML/Main/data/agaricus-lepiota.data +8124 -0
  21. noshot/data/ML TS XAI/ML/Main/data/balance-scale.txt +625 -0
  22. noshot/data/ML TS XAI/ML/Main/data/doctor-visits.csv +715 -0
  23. noshot/data/ML TS XAI/ML/Main/data/iris.csv +151 -0
  24. noshot/data/ML TS XAI/ML/Main/data/machine-data.csv +210 -0
  25. noshot/data/ML TS XAI/ML/Main/data/magic04.data +19020 -0
  26. noshot/data/ML TS XAI/ML/Main/data/real-estate.xlsx +0 -0
  27. noshot/data/ML TS XAI/ML/Main/data/rice.arff +3826 -0
  28. noshot/data/ML TS XAI/ML/Main/data/sobar-72.csv +73 -0
  29. noshot/data/ML TS XAI/ML/Main/data/wine-dataset.csv +179 -0
  30. noshot/data/ML TS XAI/ML/Other Codes.ipynb +158 -0
  31. noshot/data/ML TS XAI/ML/Rolls Royce AllinOne.ipynb +691 -0
  32. {noshot-2.0.0.dist-info → noshot-4.0.0.dist-info}/METADATA +1 -1
  33. noshot-4.0.0.dist-info/RECORD +40 -0
  34. {noshot-2.0.0.dist-info → noshot-4.0.0.dist-info}/WHEEL +1 -1
  35. noshot/data/ML TS XAI/TS/bill-charge.ipynb +0 -239
  36. noshot/data/ML TS XAI/TS/daily-min-temperatures.ipynb +0 -239
  37. noshot/data/ML TS XAI/TS/data/bill-data.csv +0 -21
  38. noshot/data/ML TS XAI/TS/data/daily-min-temperatures.csv +0 -3651
  39. noshot/data/ML TS XAI/TS/data/monthly-sunspots.csv +0 -2821
  40. noshot/data/ML TS XAI/TS/monthly-sunspots.ipynb +0 -241
  41. noshot-2.0.0.dist-info/RECORD +0 -15
  42. {noshot-2.0.0.dist-info → noshot-4.0.0.dist-info}/licenses/LICENSE.txt +0 -0
  43. {noshot-2.0.0.dist-info → noshot-4.0.0.dist-info}/top_level.txt +0 -0
noshot/data/ML TS XAI/ML/ML Lab CIA 2 (I Found Only This Check)/Copy_of_Pistachio_csv.ipynb ADDED
@@ -0,0 +1,269 @@
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ }
15
+ },
16
+ "cells": [
17
+ {
18
+ "cell_type": "markdown",
19
+ "source": [
20
+ "3.\tBuild a Feed Forward Neural Network using Keras to classify pistachio types. Your model should include dropout layers to prevent overfitting."
21
+ ],
22
+ "metadata": {
23
+ "id": "41vyXTdsmm3h"
24
+ }
25
+ },
26
+ {
27
+ "cell_type": "code",
28
+ "execution_count": 6,
29
+ "metadata": {
30
+ "colab": {
31
+ "base_uri": "https://localhost:8080/",
32
+ "height": 1000
33
+ },
34
+ "id": "HOFKtDK0kHT9",
35
+ "outputId": "18140e5f-6bb3-46fa-d79f-a097d9329417"
36
+ },
37
+ "outputs": [
38
+ {
39
+ "output_type": "stream",
40
+ "name": "stdout",
41
+ "text": [
42
+ "Epoch 1/50\n",
43
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 8ms/step - accuracy: 0.7590 - loss: 0.4845 - val_accuracy: 0.8721 - val_loss: 0.2682\n",
44
+ "Epoch 2/50\n",
45
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8751 - loss: 0.3274 - val_accuracy: 0.8547 - val_loss: 0.2538\n",
46
+ "Epoch 3/50\n",
47
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.8886 - loss: 0.2920 - val_accuracy: 0.8895 - val_loss: 0.2505\n",
48
+ "Epoch 4/50\n",
49
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.8933 - loss: 0.2681 - val_accuracy: 0.9070 - val_loss: 0.2278\n",
50
+ "Epoch 5/50\n",
51
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.8910 - loss: 0.2684 - val_accuracy: 0.9012 - val_loss: 0.2265\n",
52
+ "Epoch 6/50\n",
53
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9070 - loss: 0.2494 - val_accuracy: 0.9128 - val_loss: 0.2144\n",
54
+ "Epoch 7/50\n",
55
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9034 - loss: 0.2454 - val_accuracy: 0.9244 - val_loss: 0.2116\n",
56
+ "Epoch 8/50\n",
57
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.8987 - loss: 0.2574 - val_accuracy: 0.9360 - val_loss: 0.2095\n",
58
+ "Epoch 9/50\n",
59
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9039 - loss: 0.2324 - val_accuracy: 0.9244 - val_loss: 0.2017\n",
60
+ "Epoch 10/50\n",
61
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9132 - loss: 0.2222 - val_accuracy: 0.9360 - val_loss: 0.1927\n",
62
+ "Epoch 11/50\n",
63
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9131 - loss: 0.2119 - val_accuracy: 0.9302 - val_loss: 0.1942\n",
64
+ "Epoch 12/50\n",
65
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - accuracy: 0.9176 - loss: 0.2007 - val_accuracy: 0.9360 - val_loss: 0.1871\n",
66
+ "Epoch 13/50\n",
67
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9252 - loss: 0.2114 - val_accuracy: 0.9419 - val_loss: 0.1742\n",
68
+ "Epoch 14/50\n",
69
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9179 - loss: 0.1991 - val_accuracy: 0.9360 - val_loss: 0.1675\n",
70
+ "Epoch 15/50\n",
71
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9285 - loss: 0.1831 - val_accuracy: 0.9186 - val_loss: 0.1781\n",
72
+ "Epoch 16/50\n",
73
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9359 - loss: 0.1755 - val_accuracy: 0.9477 - val_loss: 0.1644\n",
74
+ "Epoch 17/50\n",
75
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9335 - loss: 0.1608 - val_accuracy: 0.9302 - val_loss: 0.1675\n",
76
+ "Epoch 18/50\n",
77
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9396 - loss: 0.1645 - val_accuracy: 0.9419 - val_loss: 0.1616\n",
78
+ "Epoch 19/50\n",
79
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9252 - loss: 0.1638 - val_accuracy: 0.9419 - val_loss: 0.1670\n",
80
+ "Epoch 20/50\n",
81
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9398 - loss: 0.1512 - val_accuracy: 0.9360 - val_loss: 0.1570\n",
82
+ "Epoch 21/50\n",
83
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9390 - loss: 0.1486 - val_accuracy: 0.9360 - val_loss: 0.1544\n",
84
+ "Epoch 22/50\n",
85
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9280 - loss: 0.1833 - val_accuracy: 0.9360 - val_loss: 0.1552\n",
86
+ "Epoch 23/50\n",
87
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9356 - loss: 0.1505 - val_accuracy: 0.9302 - val_loss: 0.1528\n",
88
+ "Epoch 24/50\n",
89
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9342 - loss: 0.1544 - val_accuracy: 0.9360 - val_loss: 0.1516\n",
90
+ "Epoch 25/50\n",
91
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9424 - loss: 0.1579 - val_accuracy: 0.9360 - val_loss: 0.1538\n",
92
+ "Epoch 26/50\n",
93
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9544 - loss: 0.1391 - val_accuracy: 0.9419 - val_loss: 0.1487\n",
94
+ "Epoch 27/50\n",
95
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9364 - loss: 0.1406 - val_accuracy: 0.9302 - val_loss: 0.1522\n",
96
+ "Epoch 28/50\n",
97
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9538 - loss: 0.1309 - val_accuracy: 0.9302 - val_loss: 0.1569\n",
98
+ "Epoch 29/50\n",
99
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9316 - loss: 0.1749 - val_accuracy: 0.9360 - val_loss: 0.1432\n",
100
+ "Epoch 30/50\n",
101
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9565 - loss: 0.1316 - val_accuracy: 0.9419 - val_loss: 0.1291\n",
102
+ "Epoch 31/50\n",
103
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9418 - loss: 0.1465 - val_accuracy: 0.9419 - val_loss: 0.1500\n",
104
+ "Epoch 32/50\n",
105
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9550 - loss: 0.1130 - val_accuracy: 0.9419 - val_loss: 0.1391\n",
106
+ "Epoch 33/50\n",
107
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9472 - loss: 0.1263 - val_accuracy: 0.9360 - val_loss: 0.1570\n",
108
+ "Epoch 34/50\n",
109
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9532 - loss: 0.1216 - val_accuracy: 0.9360 - val_loss: 0.1482\n",
110
+ "Epoch 35/50\n",
111
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9563 - loss: 0.1260 - val_accuracy: 0.9419 - val_loss: 0.1424\n",
112
+ "Epoch 36/50\n",
113
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 7ms/step - accuracy: 0.9568 - loss: 0.1116 - val_accuracy: 0.9419 - val_loss: 0.1261\n",
114
+ "Epoch 37/50\n",
115
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9535 - loss: 0.1131 - val_accuracy: 0.9360 - val_loss: 0.1447\n",
116
+ "Epoch 38/50\n",
117
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9616 - loss: 0.0944 - val_accuracy: 0.9477 - val_loss: 0.1399\n",
118
+ "Epoch 39/50\n",
119
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9436 - loss: 0.1280 - val_accuracy: 0.9419 - val_loss: 0.1445\n",
120
+ "Epoch 40/50\n",
121
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9523 - loss: 0.1220 - val_accuracy: 0.9419 - val_loss: 0.1236\n",
122
+ "Epoch 41/50\n",
123
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9603 - loss: 0.1084 - val_accuracy: 0.9477 - val_loss: 0.1287\n",
124
+ "Epoch 42/50\n",
125
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9630 - loss: 0.0979 - val_accuracy: 0.9419 - val_loss: 0.1456\n",
126
+ "Epoch 43/50\n",
127
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9493 - loss: 0.1248 - val_accuracy: 0.9419 - val_loss: 0.1553\n",
128
+ "Epoch 44/50\n",
129
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9574 - loss: 0.1101 - val_accuracy: 0.9419 - val_loss: 0.1454\n",
130
+ "Epoch 45/50\n",
131
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9690 - loss: 0.0842 - val_accuracy: 0.9477 - val_loss: 0.1395\n",
132
+ "Epoch 46/50\n",
133
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9654 - loss: 0.1021 - val_accuracy: 0.9477 - val_loss: 0.1504\n",
134
+ "Epoch 47/50\n",
135
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9609 - loss: 0.0964 - val_accuracy: 0.9419 - val_loss: 0.1579\n",
136
+ "Epoch 48/50\n",
137
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9578 - loss: 0.0981 - val_accuracy: 0.9477 - val_loss: 0.1415\n",
138
+ "Epoch 49/50\n",
139
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9560 - loss: 0.1128 - val_accuracy: 0.9419 - val_loss: 0.1572\n",
140
+ "Epoch 50/50\n",
141
+ "\u001b[1m49/49\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9534 - loss: 0.1044 - val_accuracy: 0.9477 - val_loss: 0.1502\n",
142
+ "\u001b[1m14/14\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.9462 - loss: 0.1061 \n",
143
+ "Test Accuracy: 0.9488\n"
144
+ ]
145
+ },
146
+ {
147
+ "output_type": "display_data",
148
+ "data": {
149
+ "text/plain": [
150
+ "<Figure size 1200x500 with 2 Axes>"
151
+ ],
152
+ "image/png": "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\n"
153
+ },
154
+ "metadata": {}
155
+ },
156
+ {
157
+ "output_type": "stream",
158
+ "name": "stdout",
159
+ "text": [
160
+ "\u001b[1m14/14\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step\n"
161
+ ]
162
+ },
163
+ {
164
+ "output_type": "display_data",
165
+ "data": {
166
+ "text/plain": [
167
+ "<Figure size 600x500 with 2 Axes>"
168
+ ],
169
+ "image/png": "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\n"
170
+ },
171
+ "metadata": {}
172
+ },
173
+ {
174
+ "output_type": "stream",
175
+ "name": "stdout",
176
+ "text": [
177
+ " precision recall f1-score support\n",
178
+ "\n",
179
+ "Kirmizi_Pistachio 0.95 0.95 0.95 244\n",
180
+ " Siirt_Pistachio 0.94 0.94 0.94 186\n",
181
+ "\n",
182
+ " accuracy 0.95 430\n",
183
+ " macro avg 0.95 0.95 0.95 430\n",
184
+ " weighted avg 0.95 0.95 0.95 430\n",
185
+ "\n"
186
+ ]
187
+ }
188
+ ],
189
+ "source": [
190
+ "import pandas as pd\n",
191
+ "import matplotlib.pyplot as plt\n",
192
+ "import seaborn as sns\n",
193
+ "import numpy as np\n",
194
+ "from sklearn.model_selection import train_test_split\n",
195
+ "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
196
+ "from sklearn.metrics import confusion_matrix, classification_report\n",
197
+ "from tensorflow.keras.models import Sequential\n",
198
+ "from tensorflow.keras.layers import Dense, Dropout\n",
199
+ "from tensorflow.keras.utils import to_categorical\n",
200
+ "\n",
201
+ "df = pd.read_csv(\"Copy of Pistachio_28_Features_Dataset.csv\")\n",
202
+ "X = df.drop(\"Class\", axis=1).values\n",
203
+ "y = df[\"Class\"].values\n",
204
+ "\n",
205
+ "label_encoder = LabelEncoder()\n",
206
+ "y_encoded = label_encoder.fit_transform(y)\n",
207
+ "y_categorical = to_categorical(y_encoded)\n",
208
+ "\n",
209
+ "X_train, X_test, y_train, y_test = train_test_split(X, y_categorical, test_size=0.2, random_state=42)\n",
210
+ "\n",
211
+ "scaler = StandardScaler()\n",
212
+ "X_train_scaled = scaler.fit_transform(X_train)\n",
213
+ "X_test_scaled = scaler.transform(X_test)\n",
214
+ "\n",
215
+ "model = Sequential([\n",
216
+ " Dense(128, activation='relu', input_shape=(X_train.shape[1],)),\n",
217
+ " Dropout(0.3),\n",
218
+ " Dense(64, activation='relu'),\n",
219
+ " Dropout(0.3),\n",
220
+ " Dense(32, activation='relu'),\n",
221
+ " Dropout(0.2),\n",
222
+ " Dense(y_categorical.shape[1], activation='softmax')\n",
223
+ "])\n",
224
+ "\n",
225
+ "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
226
+ "history = model.fit(X_train_scaled, y_train, epochs=50, batch_size=32, validation_split=0.1)\n",
227
+ "\n",
228
+ "test_loss, test_accuracy = model.evaluate(X_test_scaled, y_test)\n",
229
+ "print(f\"Test Accuracy: {test_accuracy:.4f}\")\n",
230
+ "\n",
231
+ "plt.figure(figsize=(12, 5))\n",
232
+ "plt.subplot(1, 2, 1)\n",
233
+ "plt.plot(history.history['accuracy'], label='Train Accuracy', linewidth=2)\n",
234
+ "plt.plot(history.history['val_accuracy'], label='Val Accuracy', linewidth=2)\n",
235
+ "plt.title('Accuracy over Epochs')\n",
236
+ "plt.xlabel('Epochs')\n",
237
+ "plt.ylabel('Accuracy')\n",
238
+ "plt.legend()\n",
239
+ "\n",
240
+ "plt.subplot(1, 2, 2)\n",
241
+ "plt.plot(history.history['loss'], label='Train Loss', linewidth=2)\n",
242
+ "plt.plot(history.history['val_loss'], label='Val Loss', linewidth=2)\n",
243
+ "plt.title('Loss over Epochs')\n",
244
+ "plt.xlabel('Epochs')\n",
245
+ "plt.ylabel('Loss')\n",
246
+ "plt.legend()\n",
247
+ "\n",
248
+ "plt.tight_layout()\n",
249
+ "plt.show()\n",
250
+ "\n",
251
+ "y_pred = model.predict(X_test_scaled)\n",
252
+ "y_pred_classes = np.argmax(y_pred, axis=1)\n",
253
+ "y_true_classes = np.argmax(y_test, axis=1)\n",
254
+ "\n",
255
+ "conf_matrix = confusion_matrix(y_true_classes, y_pred_classes)\n",
256
+ "plt.figure(figsize=(6, 5))\n",
257
+ "sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues',\n",
258
+ " xticklabels=label_encoder.classes_,\n",
259
+ " yticklabels=label_encoder.classes_)\n",
260
+ "plt.xlabel('Predicted')\n",
261
+ "plt.ylabel('Actual')\n",
262
+ "plt.title('Confusion Matrix')\n",
263
+ "plt.show()\n",
264
+ "\n",
265
+ "print(classification_report(y_true_classes, y_pred_classes, target_names=label_encoder.classes_))"
266
+ ]
267
+ }
268
+ ]
269
+ }