noshot 6.0.0__py3-none-any.whl → 8.0.0__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 (62) hide show
  1. noshot/data/ML TS XAI/ML/CNN(Image_for_Folders_5).ipynb +201 -0
  2. noshot/data/ML TS XAI/ML/CNN(Image_form_Folder_2).ipynb +201 -0
  3. noshot/data/ML TS XAI/ML/ML 1/1. EDA-PCA (Balance Scale Dataset).ipynb +147 -0
  4. noshot/data/ML TS XAI/ML/ML 1/1. EDA-PCA (Rice Dataset).ipynb +181 -0
  5. noshot/data/ML TS XAI/ML/ML 1/10. HMM Veterbi.ipynb +152 -0
  6. noshot/data/ML TS XAI/ML/ML 1/2. KNN (Balance Scale Dataset).ipynb +117 -0
  7. noshot/data/ML TS XAI/ML/ML 1/2. KNN (Iris Dataset).ipynb +156 -0
  8. noshot/data/ML TS XAI/ML/ML 1/2. KNN (Sobar-72 Dataset).ipynb +215 -0
  9. noshot/data/ML TS XAI/ML/ML 1/3. LDA (Balance Scale Dataset).ipynb +78 -0
  10. noshot/data/ML TS XAI/ML/ML 1/3. LDA (NPHA Doctor Visits Dataset).ipynb +114 -0
  11. noshot/data/ML TS XAI/ML/ML 1/4. Linear Regression (Machine Dataset).ipynb +115 -0
  12. noshot/data/ML TS XAI/ML/ML 1/4. Linear Regression (Real Estate Dataset).ipynb +146 -0
  13. noshot/data/ML TS XAI/ML/ML 1/5. Logistic Regression (Magic04 Dataset).ipynb +130 -0
  14. noshot/data/ML TS XAI/ML/ML 1/5. Logistic Regression (Wine Dataset).ipynb +112 -0
  15. noshot/data/ML TS XAI/ML/ML 1/6. Naive Bayes Classifier (Agaricus Lepiota Dataset).ipynb +118 -0
  16. noshot/data/ML TS XAI/ML/ML 1/6. Naive Bayes Classifier (Wine Dataset).ipynb +89 -0
  17. noshot/data/ML TS XAI/ML/ML 1/7. SVM (Rice Dataset).ipynb +120 -0
  18. noshot/data/ML TS XAI/ML/ML 1/8. FeedForward NN (Sobar72 Dataset).ipynb +262 -0
  19. noshot/data/ML TS XAI/ML/ML 1/9. CNN (Cifar10 Dataset).ipynb +156 -0
  20. noshot/data/ML TS XAI/ML/ML 2/1. PCA.ipynb +162 -0
  21. noshot/data/ML TS XAI/ML/ML 2/10. CNN.ipynb +100 -0
  22. noshot/data/ML TS XAI/ML/ML 2/11. HMM.ipynb +336 -0
  23. noshot/data/ML TS XAI/ML/ML 2/2. KNN.ipynb +149 -0
  24. noshot/data/ML TS XAI/ML/ML 2/3. LDA.ipynb +132 -0
  25. noshot/data/ML TS XAI/ML/ML 2/4. Linear Regression.ipynb +86 -0
  26. noshot/data/ML TS XAI/ML/ML 2/5. Logistic Regression.ipynb +115 -0
  27. noshot/data/ML TS XAI/ML/ML 2/6. Naive Bayes (Titanic).ipynb +196 -0
  28. noshot/data/ML TS XAI/ML/ML 2/6. Naive Bayes (Wine).ipynb +98 -0
  29. noshot/data/ML TS XAI/ML/ML 2/7. SVM Linear.ipynb +109 -0
  30. noshot/data/ML TS XAI/ML/ML 2/8. SVM Non-Linear.ipynb +195 -0
  31. noshot/data/ML TS XAI/ML/ML 2/9. FNN With Regularization.ipynb +189 -0
  32. noshot/data/ML TS XAI/ML/ML 2/9. FNN Without Regularization.ipynb +197 -0
  33. noshot/data/ML TS XAI/ML/ML 2/All in One Lab CIA 1 Q.ipynb +1087 -0
  34. noshot/data/ML TS XAI/ML/ML 3 (Latest)/1. PCA EDA.ipynb +274 -0
  35. noshot/data/ML TS XAI/ML/ML 3 (Latest)/10. CNN.ipynb +170 -0
  36. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM 2.ipynb +1087 -0
  37. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM 3.ipynb +178 -0
  38. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM 4.ipynb +185 -0
  39. noshot/data/ML TS XAI/ML/ML 3 (Latest)/11. HMM.ipynb +106 -0
  40. noshot/data/ML TS XAI/ML/ML 3 (Latest)/2. KNN.ipynb +177 -0
  41. noshot/data/ML TS XAI/ML/ML 3 (Latest)/3. LDA.ipynb +195 -0
  42. noshot/data/ML TS XAI/ML/ML 3 (Latest)/4. Linear Regression.ipynb +267 -0
  43. noshot/data/ML TS XAI/ML/ML 3 (Latest)/5. Logistic Regression.ipynb +104 -0
  44. noshot/data/ML TS XAI/ML/ML 3 (Latest)/6. Bayesian Classifier.ipynb +109 -0
  45. noshot/data/ML TS XAI/ML/ML 3 (Latest)/7. SVM.ipynb +220 -0
  46. noshot/data/ML TS XAI/ML/ML 3 (Latest)/8. MLP.ipynb +99 -0
  47. noshot/data/ML TS XAI/ML/ML 3 (Latest)/9. Ridge - Lasso.ipynb +211 -0
  48. noshot/data/ML TS XAI/ML/ML 3 (Latest)/9. Ridge Lasso 2.ipynb +99 -0
  49. noshot/data/ML TS XAI/ML/ML 3 (Latest)/Image Load Example.ipynb +118 -0
  50. noshot/data/ML TS XAI/ML/ML 3 (Latest)/Updated_Untitled.ipynb +603 -0
  51. noshot/data/ML TS XAI/ML/Rolls Royce AllinOne.ipynb +691 -0
  52. {noshot-6.0.0.dist-info → noshot-8.0.0.dist-info}/METADATA +1 -1
  53. noshot-8.0.0.dist-info/RECORD +60 -0
  54. {noshot-6.0.0.dist-info → noshot-8.0.0.dist-info}/WHEEL +1 -1
  55. noshot/data/ML TS XAI/XAI/Q1.ipynb +0 -377
  56. noshot/data/ML TS XAI/XAI/Q2.ipynb +0 -362
  57. noshot/data/ML TS XAI/XAI/Q3.ipynb +0 -637
  58. noshot/data/ML TS XAI/XAI/Q4.ipynb +0 -206
  59. noshot/data/ML TS XAI/XAI/Q5.ipynb +0 -1018
  60. noshot-6.0.0.dist-info/RECORD +0 -14
  61. {noshot-6.0.0.dist-info → noshot-8.0.0.dist-info}/licenses/LICENSE.txt +0 -0
  62. {noshot-6.0.0.dist-info → noshot-8.0.0.dist-info}/top_level.txt +0 -0
noshot/data/ML TS XAI/ML/ML 1/2. KNN (Sobar-72 Dataset).ipynb ADDED
@@ -0,0 +1,215 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "838f3d63-f48d-4003-8a20-767d87d5d63b",
7
+ "metadata": {
8
+ "id": "10424106"
9
+ },
10
+ "outputs": [],
11
+ "source": [
12
+ "import numpy as np\n",
13
+ "import pandas as pd\n",
14
+ "import seaborn as sns\n",
15
+ "import matplotlib.pyplot as plt\n",
16
+ "from sklearn.model_selection import train_test_split\n",
17
+ "from sklearn.preprocessing import StandardScaler\n",
18
+ "from sklearn.decomposition import PCA\n",
19
+ "from sklearn.neighbors import KNeighborsClassifier\n",
20
+ "from sklearn import metrics\n",
21
+ "from mlxtend.plotting import plot_decision_regions\n",
22
+ "from scipy.cluster.hierarchy import dendrogram, linkage\n",
23
+ "from scipy.spatial import Voronoi, voronoi_plot_2d"
24
+ ]
25
+ },
26
+ {
27
+ "cell_type": "code",
28
+ "execution_count": null,
29
+ "id": "5a30696e-2e04-4ead-90c7-21dbd6b1d75d",
30
+ "metadata": {
31
+ "id": "10424106"
32
+ },
33
+ "outputs": [],
34
+ "source": [
35
+ "df = pd.read_csv(\"data/sobar-72.csv\")\n",
36
+ "display(df.head())\n",
37
+ "display(df.info())"
38
+ ]
39
+ },
40
+ {
41
+ "cell_type": "code",
42
+ "execution_count": null,
43
+ "id": "35e3b9f1-f5ed-4dd1-8a4d-aeb7fe77bea2",
44
+ "metadata": {
45
+ "id": "10424106"
46
+ },
47
+ "outputs": [],
48
+ "source": [
49
+ "cols = [\n",
50
+ " 'behavior_sexualRisk', 'intention_aggregation', 'attitude_consistency',\n",
51
+ " 'norm_significantPerson', 'perception_vulnerability', 'motivation_strength',\n",
52
+ " 'socialSupport_emotionality', 'empowerment_knowledge', 'ca_cervix'\n",
53
+ "]\n",
54
+ "sns.pairplot(df[cols], hue='ca_cervix')\n",
55
+ "plt.show()"
56
+ ]
57
+ },
58
+ {
59
+ "cell_type": "code",
60
+ "execution_count": null,
61
+ "id": "09bb4a6d-3807-44cb-b15e-2e6b3ff20d02",
62
+ "metadata": {
63
+ "id": "10424106"
64
+ },
65
+ "outputs": [],
66
+ "source": [
67
+ "X = df.drop(columns=['ca_cervix'])\n",
68
+ "y = df['ca_cervix']"
69
+ ]
70
+ },
71
+ {
72
+ "cell_type": "code",
73
+ "execution_count": null,
74
+ "id": "5a235b36-2136-4924-a6a3-834fde3e541c",
75
+ "metadata": {
76
+ "id": "10424106"
77
+ },
78
+ "outputs": [],
79
+ "source": [
80
+ "X_scaled = StandardScaler().fit_transform(X)\n",
81
+ "X_pca = PCA(n_components=2).fit_transform(X_scaled)\n",
82
+ "X_train, X_test, y_train, y_test = train_test_split(X_pca, y, test_size=0.4, random_state=4)"
83
+ ]
84
+ },
85
+ {
86
+ "cell_type": "code",
87
+ "execution_count": null,
88
+ "id": "7db3c778-fb6f-4509-8598-5df6928058e2",
89
+ "metadata": {
90
+ "id": "10424106"
91
+ },
92
+ "outputs": [],
93
+ "source": [
94
+ "similarities = ['euclidean', 'manhattan', 'minkowski']\n",
95
+ "for sim in similarities:\n",
96
+ " knn = KNeighborsClassifier(n_neighbors=5, metric=sim)\n",
97
+ " knn.fit(X_train, y_train)\n",
98
+ " y_pred = knn.predict(X_test)\n",
99
+ "\n",
100
+ " plot_decision_regions(X_train, np.array(y_train), clf=knn, legend=2)\n",
101
+ " plt.xlabel('X')\n",
102
+ " plt.ylabel('Y')\n",
103
+ " plt.title(f'KNN with K=5 using {sim.capitalize()} Distance')\n",
104
+ " plt.show()"
105
+ ]
106
+ },
107
+ {
108
+ "cell_type": "code",
109
+ "execution_count": null,
110
+ "id": "f4fee956-56f9-487d-b1fd-a2c32536fa0f",
111
+ "metadata": {
112
+ "id": "10424106"
113
+ },
114
+ "outputs": [],
115
+ "source": [
116
+ "k_values, accuracies = [], []\n",
117
+ "for k in range(1, 10):\n",
118
+ " knn = KNeighborsClassifier(n_neighbors=k)\n",
119
+ " knn.fit(X_train, y_train)\n",
120
+ " y_pred = knn.predict(X_test)\n",
121
+ " k_values.append(k)\n",
122
+ " accuracies.append(metrics.accuracy_score(y_test, y_pred))\n",
123
+ "\n",
124
+ "plt.figure(figsize=(4, 2))\n",
125
+ "plt.plot(k_values, accuracies, marker='o')\n",
126
+ "plt.title('K Value vs Accuracy')\n",
127
+ "plt.xlabel('K')\n",
128
+ "plt.ylabel('Accuracy')\n",
129
+ "plt.grid()\n",
130
+ "plt.show()"
131
+ ]
132
+ },
133
+ {
134
+ "cell_type": "code",
135
+ "execution_count": null,
136
+ "id": "6ecc3e38-c791-48eb-ad01-a8149a2380ae",
137
+ "metadata": {
138
+ "id": "10424106"
139
+ },
140
+ "outputs": [],
141
+ "source": [
142
+ "plt.scatter(X_test[:, 0], X_test[:, 1], c=y_pred, cmap='coolwarm', edgecolors='k')\n",
143
+ "plt.title('Test Data Predictions')\n",
144
+ "plt.grid()\n",
145
+ "plt.show()"
146
+ ]
147
+ },
148
+ {
149
+ "cell_type": "code",
150
+ "execution_count": null,
151
+ "id": "9f40e9af-601f-4b4e-aadc-c3b27d4e4f11",
152
+ "metadata": {
153
+ "id": "10424106"
154
+ },
155
+ "outputs": [],
156
+ "source": [
157
+ "unique_labels = np.unique(y)\n",
158
+ "label_mapping = {label: i for i, label in enumerate(unique_labels)}\n",
159
+ "y_mapped = np.array([label_mapping[label] for label in y])\n",
160
+ "\n",
161
+ "linked = linkage(X_pca, method='single')\n",
162
+ "\n",
163
+ "plt.figure(figsize=(10, 7))\n",
164
+ "dendrogram(linked, orientation='top', distance_sort='descending', labels=y_mapped, show_leaf_counts=True)\n",
165
+ "plt.title('Dendrogram for KNN')\n",
166
+ "plt.xlabel('Data Points')\n",
167
+ "plt.ylabel('Distance')\n",
168
+ "plt.show()"
169
+ ]
170
+ },
171
+ {
172
+ "cell_type": "code",
173
+ "execution_count": null,
174
+ "id": "5164b3a8-26f4-4855-a551-d5f9790b9975",
175
+ "metadata": {
176
+ "id": "10424106"
177
+ },
178
+ "outputs": [],
179
+ "source": [
180
+ "vor = Voronoi(X_pca)\n",
181
+ "fig = voronoi_plot_2d(vor, show_vertices=False, line_colors='black', line_width=2, line_alpha=0.6, point_size=10)\n",
182
+ "\n",
183
+ "plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='viridis', s=50, edgecolors='k')\n",
184
+ "plt.title('Voronoi Diagram with Target Variable')\n",
185
+ "plt.xlabel('X')\n",
186
+ "plt.ylabel('Y')\n",
187
+ "plt.show()"
188
+ ]
189
+ }
190
+ ],
191
+ "metadata": {
192
+ "colab": {
193
+ "provenance": []
194
+ },
195
+ "kernelspec": {
196
+ "display_name": "Python 3 (ipykernel)",
197
+ "language": "python",
198
+ "name": "python3"
199
+ },
200
+ "language_info": {
201
+ "codemirror_mode": {
202
+ "name": "ipython",
203
+ "version": 3
204
+ },
205
+ "file_extension": ".py",
206
+ "mimetype": "text/x-python",
207
+ "name": "python",
208
+ "nbconvert_exporter": "python",
209
+ "pygments_lexer": "ipython3",
210
+ "version": "3.12.4"
211
+ }
212
+ },
213
+ "nbformat": 4,
214
+ "nbformat_minor": 5
215
+ }
noshot/data/ML TS XAI/ML/ML 1/3. LDA (Balance Scale Dataset).ipynb ADDED
@@ -0,0 +1,78 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "96ac04a5-6577-4da4-8454-3b10535351f8",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import pandas as pd\n",
11
+ "import matplotlib.pyplot as plt\n",
12
+ "from sklearn.preprocessing import StandardScaler\n",
13
+ "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA"
14
+ ]
15
+ },
16
+ {
17
+ "cell_type": "code",
18
+ "execution_count": null,
19
+ "id": "b1ffa4dc-488f-4238-877b-5cbd6fb48e4e",
20
+ "metadata": {},
21
+ "outputs": [],
22
+ "source": [
23
+ "cols = ['class name','left-weight','left-distance','right-weight','right-distance']\n",
24
+ "df = pd.read_table('data/balance-scale.txt', delimiter = \",\", names=cols)\n",
25
+ "print(\"Shape:\", df.shape)\n",
26
+ "df.head()"
27
+ ]
28
+ },
29
+ {
30
+ "cell_type": "code",
31
+ "execution_count": null,
32
+ "id": "069bba36-4187-48e4-bc5b-d1443c1ee87c",
33
+ "metadata": {},
34
+ "outputs": [],
35
+ "source": [
36
+ "features = ['left-weight','left-distance','right-weight','right-distance']\n",
37
+ "x = df.loc[:,features]\n",
38
+ "y = df.loc[:,'class name']\n",
39
+ "lda = LDA(n_components=2)\n",
40
+ "lda_X = lda.fit(x,y).transform(x)"
41
+ ]
42
+ },
43
+ {
44
+ "cell_type": "code",
45
+ "execution_count": null,
46
+ "id": "66c2b6ac-6163-4f36-ae6b-3a9e32e578ce",
47
+ "metadata": {},
48
+ "outputs": [],
49
+ "source": [
50
+ "plt.scatter(lda_X[y == 'L', 0], lda_X[y == 'L', 1], s=50, c='orange', label='L')\n",
51
+ "plt.scatter(lda_X[y == 'B', 0], lda_X[y == 'B', 1], s=50, c='blue', label='B')\n",
52
+ "plt.scatter(lda_X[y == 'R', 0], lda_X[y == 'R', 1], s=50, c='green', label='R')\n",
53
+ "plt.title('LDA plot for cmc DataSet')"
54
+ ]
55
+ }
56
+ ],
57
+ "metadata": {
58
+ "kernelspec": {
59
+ "display_name": "Python 3 (ipykernel)",
60
+ "language": "python",
61
+ "name": "python3"
62
+ },
63
+ "language_info": {
64
+ "codemirror_mode": {
65
+ "name": "ipython",
66
+ "version": 3
67
+ },
68
+ "file_extension": ".py",
69
+ "mimetype": "text/x-python",
70
+ "name": "python",
71
+ "nbconvert_exporter": "python",
72
+ "pygments_lexer": "ipython3",
73
+ "version": "3.12.4"
74
+ }
75
+ },
76
+ "nbformat": 4,
77
+ "nbformat_minor": 5
78
+ }
noshot/data/ML TS XAI/ML/ML 1/3. LDA (NPHA Doctor Visits Dataset).ipynb ADDED
@@ -0,0 +1,114 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "68f40eda",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import pandas as pd\n",
11
+ "import numpy as np\n",
12
+ "import matplotlib.pyplot as plt"
13
+ ]
14
+ },
15
+ {
16
+ "cell_type": "code",
17
+ "execution_count": null,
18
+ "id": "066999b2",
19
+ "metadata": {},
20
+ "outputs": [],
21
+ "source": [
22
+ "df = pd.read_csv(r\"data\\doctor-visits.csv\")\n",
23
+ "print(\"Shape:\", df.shape)\n",
24
+ "df.head()"
25
+ ]
26
+ },
27
+ {
28
+ "cell_type": "code",
29
+ "execution_count": null,
30
+ "id": "839d6a31",
31
+ "metadata": {},
32
+ "outputs": [],
33
+ "source": [
34
+ "df.columns"
35
+ ]
36
+ },
37
+ {
38
+ "cell_type": "code",
39
+ "execution_count": null,
40
+ "id": "7d105e4c",
41
+ "metadata": {},
42
+ "outputs": [],
43
+ "source": [
44
+ "X = df.drop(columns=['Number of Doctors Visited'])\n",
45
+ "Y = df['Number of Doctors Visited']"
46
+ ]
47
+ },
48
+ {
49
+ "cell_type": "code",
50
+ "execution_count": null,
51
+ "id": "05dc3f49-79f4-4862-91e8-89aab4ae2b2f",
52
+ "metadata": {},
53
+ "outputs": [],
54
+ "source": [
55
+ "from sklearn import metrics\n",
56
+ "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
57
+ "from sklearn.model_selection import train_test_split\n",
58
+ "\n",
59
+ "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.4, random_state=4)\n",
60
+ "\n",
61
+ "lda = LinearDiscriminantAnalysis(n_components=2)\n",
62
+ "X_train = lda.fit_transform(X_train, y_train)\n",
63
+ "X_test = lda.fit_transform(X_test,y_test)"
64
+ ]
65
+ },
66
+ {
67
+ "cell_type": "code",
68
+ "execution_count": null,
69
+ "id": "9e25c024-8dd8-40da-b755-1ed36dfc197c",
70
+ "metadata": {},
71
+ "outputs": [],
72
+ "source": [
73
+ "lda.fit(X_train,y_train)\n",
74
+ "y_pred=lda.predict(X_test)\n",
75
+ "print (\"Accuracy:\",metrics.accuracy_score(y_test, y_pred))"
76
+ ]
77
+ },
78
+ {
79
+ "cell_type": "code",
80
+ "execution_count": null,
81
+ "id": "7f0537a8-6820-4859-a3f5-f24096dfa66b",
82
+ "metadata": {},
83
+ "outputs": [],
84
+ "source": [
85
+ "plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap='viridis')\n",
86
+ "plt.title('LDA Dimensionality Reduction')\n",
87
+ "plt.xlabel('LDA Component 1')\n",
88
+ "plt.ylabel('LDA Component 2')\n",
89
+ "plt.show()"
90
+ ]
91
+ }
92
+ ],
93
+ "metadata": {
94
+ "kernelspec": {
95
+ "display_name": "Python 3 (ipykernel)",
96
+ "language": "python",
97
+ "name": "python3"
98
+ },
99
+ "language_info": {
100
+ "codemirror_mode": {
101
+ "name": "ipython",
102
+ "version": 3
103
+ },
104
+ "file_extension": ".py",
105
+ "mimetype": "text/x-python",
106
+ "name": "python",
107
+ "nbconvert_exporter": "python",
108
+ "pygments_lexer": "ipython3",
109
+ "version": "3.12.4"
110
+ }
111
+ },
112
+ "nbformat": 4,
113
+ "nbformat_minor": 5
114
+ }
noshot/data/ML TS XAI/ML/ML 1/4. Linear Regression (Machine Dataset).ipynb ADDED
@@ -0,0 +1,115 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "2d42ca1a-531d-4d5b-aee4-a489d5033d1b",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import pandas as pd\n",
11
+ "import matplotlib.pyplot as plt\n",
12
+ "from sklearn.model_selection import train_test_split\n",
13
+ "from sklearn.linear_model import LinearRegression\n",
14
+ "from sklearn.metrics import r2_score"
15
+ ]
16
+ },
17
+ {
18
+ "cell_type": "code",
19
+ "execution_count": null,
20
+ "id": "f81220bc-5415-4b02-b2fd-fd5a8ff8c97a",
21
+ "metadata": {},
22
+ "outputs": [],
23
+ "source": [
24
+ "df = pd.read_csv('data/machine-data.csv')\n",
25
+ "print(\"Shape:\", df.shape)\n",
26
+ "df.head()"
27
+ ]
28
+ },
29
+ {
30
+ "cell_type": "code",
31
+ "execution_count": null,
32
+ "id": "958f3a04-3ae7-442b-a6e7-9134b9c5aeb3",
33
+ "metadata": {},
34
+ "outputs": [],
35
+ "source": [
36
+ "x = df.iloc[:,3:4].values\n",
37
+ "y = df.iloc[:,8].values\n",
38
+ "\n",
39
+ "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 0)\n",
40
+ "regressor = LinearRegression()\n",
41
+ "regressor.fit(X_train, y_train)"
42
+ ]
43
+ },
44
+ {
45
+ "cell_type": "code",
46
+ "execution_count": null,
47
+ "id": "5b15fa5c-5c78-436b-8f33-4f431c797788",
48
+ "metadata": {},
49
+ "outputs": [],
50
+ "source": [
51
+ "y_pred = regressor.predict(X_test)\n",
52
+ "y_pred_train = regressor.predict(X_train)\n",
53
+ "print(\"Model Score: \", regressor.score(X_test, y_test))\n",
54
+ "print(\"R2 Score: \", r2_score(y_test, y_pred))"
55
+ ]
56
+ },
57
+ {
58
+ "cell_type": "code",
59
+ "execution_count": null,
60
+ "id": "b044ea95-014e-466b-b036-8ba9f96e3910",
61
+ "metadata": {},
62
+ "outputs": [],
63
+ "source": [
64
+ "plt.scatter(X_train, y_train, color = 'red')\n",
65
+ "plt.plot(X_train, regressor.predict(X_train), color = 'blue')\n",
66
+ "plt.title('Y vs X (Training set)')\n",
67
+ "plt.xlabel('X')\n",
68
+ "plt.ylabel('Y')\n",
69
+ "plt.show()\n",
70
+ "plt.scatter(X_test, y_test, color = 'red')\n",
71
+ "plt.plot(X_train, regressor.predict(X_train), color = 'blue')\n",
72
+ "plt.title('Y vs X (Test set)')\n",
73
+ "plt.xlabel('X')"
74
+ ]
75
+ },
76
+ {
77
+ "cell_type": "code",
78
+ "execution_count": null,
79
+ "id": "33c64414-d432-439e-a976-d28a9b4c3f2a",
80
+ "metadata": {},
81
+ "outputs": [],
82
+ "source": [
83
+ "X_future_expereince = [[2],[4]]\n",
84
+ "print(\"Prediction :\", regressor.predict(X_future_expereince))\n",
85
+ "plt.scatter(X_future_expereince, regressor.predict(X_future_expereince), color = 'red')\n",
86
+ "plt.plot(X_train, regressor.predict(X_train), color = 'blue')\n",
87
+ "plt.title('Y vs X (Test set)')\n",
88
+ "plt.xlabel('X')\n",
89
+ "plt.ylabel('Y')\n",
90
+ "plt.show()"
91
+ ]
92
+ }
93
+ ],
94
+ "metadata": {
95
+ "kernelspec": {
96
+ "display_name": "Python 3 (ipykernel)",
97
+ "language": "python",
98
+ "name": "python3"
99
+ },
100
+ "language_info": {
101
+ "codemirror_mode": {
102
+ "name": "ipython",
103
+ "version": 3
104
+ },
105
+ "file_extension": ".py",
106
+ "mimetype": "text/x-python",
107
+ "name": "python",
108
+ "nbconvert_exporter": "python",
109
+ "pygments_lexer": "ipython3",
110
+ "version": "3.12.4"
111
+ }
112
+ },
113
+ "nbformat": 4,
114
+ "nbformat_minor": 5
115
+ }
noshot/data/ML TS XAI/ML/ML 1/4. Linear Regression (Real Estate Dataset).ipynb ADDED
@@ -0,0 +1,146 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "c885166e-e06f-46c2-bfe0-bc9b64e7e1e5",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import numpy as np\n",
11
+ "import pandas as pd\n",
12
+ "import seaborn as sns\n",
13
+ "import matplotlib.pyplot as plt\n",
14
+ "from sklearn.model_selection import train_test_split"
15
+ ]
16
+ },
17
+ {
18
+ "cell_type": "code",
19
+ "execution_count": null,
20
+ "id": "b00fd97c-b199-41f0-825a-4b9574967f5f",
21
+ "metadata": {},
22
+ "outputs": [],
23
+ "source": [
24
+ "df = pd.read_excel(\"data/real-estate.xlsx\")\n",
25
+ "df.head()"
26
+ ]
27
+ },
28
+ {
29
+ "cell_type": "code",
30
+ "execution_count": null,
31
+ "id": "90bb7a26-1e9b-4cc1-b104-ee76588ae090",
32
+ "metadata": {},
33
+ "outputs": [],
34
+ "source": [
35
+ "df.isnull().sum()"
36
+ ]
37
+ },
38
+ {
39
+ "cell_type": "code",
40
+ "execution_count": null,
41
+ "id": "9be23824-cb35-4c3c-9173-8dd99a3a2ec4",
42
+ "metadata": {},
43
+ "outputs": [],
44
+ "source": [
45
+ "sns.pairplot(df)\n",
46
+ "plt.show()"
47
+ ]
48
+ },
49
+ {
50
+ "cell_type": "code",
51
+ "execution_count": null,
52
+ "id": "517a7b77-ba3b-42d4-9941-c386c1d5b8f6",
53
+ "metadata": {},
54
+ "outputs": [],
55
+ "source": [
56
+ "sns.heatmap(df.corr(), annot=True, fmt='.2f', cmap='coolwarm')\n",
57
+ "plt.title('Correlation Heatmap')\n",
58
+ "plt.show()"
59
+ ]
60
+ },
61
+ {
62
+ "cell_type": "code",
63
+ "execution_count": null,
64
+ "id": "7b3b0dc7-366e-4d69-a537-27856bc39643",
65
+ "metadata": {},
66
+ "outputs": [],
67
+ "source": [
68
+ "def lin_reg(colX):\n",
69
+ " X = df[colX].values\n",
70
+ " y = df['Y house price of unit area'].values\n",
71
+ "\n",
72
+ " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
73
+ "\n",
74
+ " N = len(X_train)\n",
75
+ " beta1 = (N * np.sum(X_train * y_train) - np.sum(X_train) * np.sum(y_train)) / (N * np.sum(X_train ** 2) - (np.sum(X_train)) ** 2)\n",
76
+ " beta0 = (np.sum(y_train) - beta1 * np.sum(X_train)) / N\n",
77
+ "\n",
78
+ " y_pred_train = beta1 * X_train + beta0\n",
79
+ " y_pred_test = beta1 * X_test + beta0\n",
80
+ "\n",
81
+ " plt.figure(figsize=(8, 5))\n",
82
+ " plt.scatter(X_train, y_train, color='blue', label='Train Data')\n",
83
+ " plt.scatter(X_test, y_test, color='green', label='Test Data')\n",
84
+ " x_line = np.linspace(min(X.min(), X_test.min()), max(X.max(), X_test.max()), 100)\n",
85
+ " y_line = beta1 * x_line + beta0\n",
86
+ " plt.plot(x_line, y_line, color='red', linewidth=2, label='Fitted Line')\n",
87
+ " plt.xlabel(colX)\n",
88
+ " plt.ylabel('Y house price of unit area')\n",
89
+ " plt.title(f'Linear Regression: {colX} vs Y')\n",
90
+ " plt.legend()\n",
91
+ " plt.grid(True)\n",
92
+ " plt.show()\n",
93
+ "\n",
94
+ " mse_train = np.mean((y_train - beta1 * X_train - beta0) ** 2)\n",
95
+ " mse_test = np.mean((y_test - beta1 * X_test - beta0) ** 2)\n",
96
+ "\n",
97
+ " return mse_train, mse_test"
98
+ ]
99
+ },
100
+ {
101
+ "cell_type": "code",
102
+ "execution_count": null,
103
+ "id": "341f4931-35d0-4a8b-a971-81e2376ad1a1",
104
+ "metadata": {},
105
+ "outputs": [],
106
+ "source": [
107
+ "mse1 = lin_reg('X3 distance to the nearest MRT station')\n",
108
+ "mse2 = lin_reg('X5 latitude')\n",
109
+ "mse3 = lin_reg('X6 longitude')"
110
+ ]
111
+ },
112
+ {
113
+ "cell_type": "code",
114
+ "execution_count": null,
115
+ "id": "6e5e18a2-00bf-4443-900d-b470ff4bd150",
116
+ "metadata": {},
117
+ "outputs": [],
118
+ "source": [
119
+ "print(mse1)\n",
120
+ "print(mse2)\n",
121
+ "print(mse3)"
122
+ ]
123
+ }
124
+ ],
125
+ "metadata": {
126
+ "kernelspec": {
127
+ "display_name": "Python 3 (ipykernel)",
128
+ "language": "python",
129
+ "name": "python3"
130
+ },
131
+ "language_info": {
132
+ "codemirror_mode": {
133
+ "name": "ipython",
134
+ "version": 3
135
+ },
136
+ "file_extension": ".py",
137
+ "mimetype": "text/x-python",
138
+ "name": "python",
139
+ "nbconvert_exporter": "python",
140
+ "pygments_lexer": "ipython3",
141
+ "version": "3.12.4"
142
+ }
143
+ },
144
+ "nbformat": 4,
145
+ "nbformat_minor": 5
146
+ }