├── 0. datasets link.txt
├── 7_1_4_Building_Linear_Regression_from_scratch_in_Python.ipynb
├── 7_1_5_Implementing_Linear_Regression_from_scratch_in_Python.ipynb
├── 7_1_5_Lin_Reg_implementation.ipynb
├── 7_2_5_Building_Logistic_Regression_from_scratch_in_Python.ipynb
├── 7_2_6_Implementing_Logistic_Regression_from_scratch_in_Python.ipynb
├── 7_2_6_Logistic_Regression_Implementation.ipynb
├── 7_3_6_Building_Support_Vector_Machine_Classifier_from_Scratch_in_Python.ipynb
├── 7_3_7_Implementing_SVM_Classifier_from_Scratch_in_Python.ipynb
├── 7_3_7_Implementing_SVM_from_Scratch.ipynb
├── 7_4_4_Building_Lasso_Regression_from_Scratch_in_Python.ipynb
└── 7_4_5_Implementing_Lasso_Regression_from_Scratch.ipynb
/0. datasets link.txt:
--------------------------------------------------------------------------------
1 | All Datasets link: https://drive.google.com/drive/folders/1BJLh_8Kx88V6ItrdLA5CQ63RIFcjKkFV?usp=sharing
2 |
--------------------------------------------------------------------------------
/7_1_4_Building_Linear_Regression_from_scratch_in_Python.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "provenance": [],
7 | "collapsed_sections": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | },
13 | "language_info": {
14 | "name": "python"
15 | }
16 | },
17 | "cells": [
18 | {
19 | "cell_type": "markdown",
20 | "metadata": {
21 | "id": "GmDgN3q0rw6y"
22 | },
23 | "source": [
24 | "Linear Regression:\n",
25 | "\n",
26 | "**Y = wX + b**\n",
27 | "\n",
28 | "Y --> Dependent Variable\n",
29 | "\n",
30 | "X --> Independent Variable\n",
31 | "\n",
32 | "w --> weight\n",
33 | "\n",
34 | "b --> bias"
35 | ]
36 | },
37 | {
38 | "cell_type": "markdown",
39 | "metadata": {
40 | "id": "X8OJXGuPvDt2"
41 | },
42 | "source": [
43 | "**Gradient Descent:**\n",
44 | "\n",
45 | "Gradient Descent is an optimization algorithm used for minimizing the loss function in various machine learning algorithms. It is used for updating the parameters of the learning model.\n",
46 | "\n",
47 | "w = w - α*dw\n",
48 | "\n",
49 | "b = b - α*db"
50 | ]
51 | },
52 | {
53 | "cell_type": "markdown",
54 | "metadata": {
55 | "id": "WSAfYP7WmECB"
56 | },
57 | "source": [
58 | "**Learning Rate:**\n",
59 | "\n",
60 | "Learning rate is a tuning parameter in an optimization algorithm that determines the step size at each iteration while moving toward a minimum of a loss function."
61 | ]
62 | },
63 | {
64 | "cell_type": "markdown",
65 | "metadata": {
66 | "id": "rkCM1toLm7oz"
67 | },
68 | "source": [
69 | ""
70 | ]
71 | },
72 | {
73 | "cell_type": "markdown",
74 | "metadata": {
75 | "id": "eSdmQl4Sm_ft"
76 | },
77 | "source": [
78 | ""
79 | ]
80 | },
81 | {
82 | "cell_type": "code",
83 | "metadata": {
84 | "id": "cNxq7tuqllsx"
85 | },
86 | "source": [
87 | "# importing numpy library\n",
88 | "import numpy as np"
89 | ],
90 | "execution_count": null,
91 | "outputs": []
92 | },
93 | {
94 | "cell_type": "markdown",
95 | "metadata": {
96 | "id": "VrbQ5F8etU0G"
97 | },
98 | "source": [
99 | "**Linear Regression**"
100 | ]
101 | },
102 | {
103 | "cell_type": "code",
104 | "metadata": {
105 | "id": "d4zf9fMJtTeW"
106 | },
107 | "source": [
108 | "class Linear_Regression():\n",
109 | "\n",
110 | " # initiating the parameters (learning rate & no. of iterations)\n",
111 | " def __init__(self, learning_rate, no_of_iterations):\n",
112 | "\n",
113 | " self.learning_rate = learning_rate\n",
114 | " self.no_of_iterations = no_of_iterations\n",
115 | "\n",
116 | "\n",
117 | " def fit(self, X, Y ):\n",
118 | "\n",
119 | " # number of training examples & number of features\n",
120 | "\n",
121 | " self.m, self.n = X.shape # number of rows & columns\n",
122 | "\n",
123 | " # initiating the weight and bias \n",
124 | "\n",
125 | " self.w = np.zeros(self.n)\n",
126 | " self.b = 0\n",
127 | " self.X = X\n",
128 | " self.Y = Y\n",
129 | "\n",
130 | " # implementing Gradient Descent\n",
131 | " \n",
132 | " for i in range(self.no_of_iterations):\n",
133 | " self.update_weights()\n",
134 | "\n",
135 | "\n",
136 | " def update_weights(self):\n",
137 | "\n",
138 | " Y_prediction = self.predict(self.X)\n",
139 | "\n",
140 | " # calculate gradients\n",
141 | "\n",
142 | " dw = - (2 * (self.X.T).dot(self.Y - Y_prediction)) / self.m\n",
143 | "\n",
144 | " db = - 2 * np.sum(self.Y - Y_prediction)/self.m\n",
145 | "\n",
146 | " # upadating the weights\n",
147 | " \n",
148 | " self.w = self.w - self.learning_rate*dw\n",
149 | " self.b = selb.b - self.learning_rate*db\n",
150 | " \n",
151 | "\n",
152 | " def predict(self, X):\n",
153 | "\n",
154 | " return X.dot(self.w) + self.b\n",
155 | "\n"
156 | ],
157 | "execution_count": null,
158 | "outputs": []
159 | }
160 | ]
161 | }
--------------------------------------------------------------------------------
/7_1_5_Implementing_Linear_Regression_from_scratch_in_Python.ipynb:
--------------------------------------------------------------------------------
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 | "metadata": {
20 | "id": "GmDgN3q0rw6y"
21 | },
22 | "source": [
23 | "Linear Regression:\n",
24 | "\n",
25 | "**Y = wX + b**\n",
26 | "\n",
27 | "Y --> Dependent Variable\n",
28 | "\n",
29 | "X --> Independent Variable\n",
30 | "\n",
31 | "w --> weight\n",
32 | "\n",
33 | "b --> bias"
34 | ]
35 | },
36 | {
37 | "cell_type": "markdown",
38 | "metadata": {
39 | "id": "X8OJXGuPvDt2"
40 | },
41 | "source": [
42 | "**Gradient Descent:**\n",
43 | "\n",
44 | "Gradient Descent is an optimization algorithm used for minimizing the loss function in various machine learning algorithms. It is used for updating the parameters of the learning model.\n",
45 | "\n",
46 | "w = w - α*dw\n",
47 | "\n",
48 | "b = b - α*db"
49 | ]
50 | },
51 | {
52 | "cell_type": "markdown",
53 | "metadata": {
54 | "id": "m4IWNi9WwNI5"
55 | },
56 | "source": [
57 | "Importing the Dependencies"
58 | ]
59 | },
60 | {
61 | "cell_type": "code",
62 | "metadata": {
63 | "id": "WtObJGwFnINT"
64 | },
65 | "source": [
66 | "# Importing numpy library\n",
67 | "import numpy as np"
68 | ],
69 | "execution_count": null,
70 | "outputs": []
71 | },
72 | {
73 | "cell_type": "markdown",
74 | "metadata": {
75 | "id": "POvc3KnRNboc"
76 | },
77 | "source": [
78 | "**Linear Regression**"
79 | ]
80 | },
81 | {
82 | "cell_type": "code",
83 | "metadata": {
84 | "id": "BuflF8sGNQXF"
85 | },
86 | "source": [
87 | "class Linear_Regression():\n",
88 | "\n",
89 | " def __init__( self, learning_rate, no_of_iterations ) :\n",
90 | " \n",
91 | " self.learning_rate = learning_rate\n",
92 | " \n",
93 | " self.no_of_iterations = no_of_iterations\n",
94 | "\n",
95 | " # fit function to train the model\n",
96 | "\n",
97 | " def fit( self, X, Y ) :\n",
98 | " \n",
99 | " # no_of_training_examples, no_of_features\n",
100 | " \n",
101 | " self.m, self.n = X.shape\n",
102 | " \n",
103 | " # initiating the weight and bias\n",
104 | " \n",
105 | " self.w = np.zeros( self.n )\n",
106 | " \n",
107 | " self.b = 0\n",
108 | " \n",
109 | " self.X = X\n",
110 | " \n",
111 | " self.Y = Y\n",
112 | "\n",
113 | "\n",
114 | " # implementing Gradient Descent for Optimization\n",
115 | " \n",
116 | " for i in range( self.no_of_iterations ) :\n",
117 | " \n",
118 | " self.update_weights()\n",
119 | " \n",
120 | " \n",
121 | " \n",
122 | " # function to update weights in gradient descent\n",
123 | " \n",
124 | " def update_weights( self ) :\n",
125 | " \n",
126 | " Y_prediction = self.predict( self.X )\n",
127 | " \n",
128 | " # calculate gradients \n",
129 | " \n",
130 | " dw = - ( 2 * ( self.X.T ).dot( self.Y - Y_prediction ) ) / self.m\n",
131 | " \n",
132 | " db = - 2 * np.sum( self.Y - Y_prediction ) / self.m \n",
133 | " \n",
134 | " # updating the weights\n",
135 | " \n",
136 | " self.w = self.w - self.learning_rate * dw\n",
137 | " \n",
138 | " self.b = self.b - self.learning_rate * db\n",
139 | " \n",
140 | " \n",
141 | " # Line function for prediction:\n",
142 | " \n",
143 | " def predict( self, X ) :\n",
144 | " \n",
145 | " return X.dot( self.w ) + self.b\n"
146 | ],
147 | "execution_count": null,
148 | "outputs": []
149 | },
150 | {
151 | "cell_type": "markdown",
152 | "metadata": {
153 | "id": "099oR2Ip8qgA"
154 | },
155 | "source": [
156 | "Using Linear Regression model for Prediction"
157 | ]
158 | },
159 | {
160 | "cell_type": "code",
161 | "metadata": {
162 | "id": "JWDqO3zw8t6P"
163 | },
164 | "source": [
165 | "# importing the dependencies\n",
166 | "import pandas as pd\n",
167 | "from sklearn.model_selection import train_test_split\n",
168 | "import matplotlib.pyplot as plt"
169 | ],
170 | "execution_count": null,
171 | "outputs": []
172 | },
173 | {
174 | "cell_type": "markdown",
175 | "metadata": {
176 | "id": "iPX7bNko_QJO"
177 | },
178 | "source": [
179 | "Data Pre-Processing"
180 | ]
181 | },
182 | {
183 | "cell_type": "code",
184 | "metadata": {
185 | "id": "_xcrhXnm_K-m"
186 | },
187 | "source": [
188 | "# loading the data from csv file to a pandas dataframe\n",
189 | "\n",
190 | "salary_data = pd.read_csv('/content/salary_data.csv')"
191 | ],
192 | "execution_count": null,
193 | "outputs": []
194 | },
195 | {
196 | "cell_type": "code",
197 | "metadata": {
198 | "colab": {
199 | "base_uri": "https://localhost:8080/",
200 | "height": 206
201 | },
202 | "id": "gkF0Gvxm_sU6",
203 | "outputId": "d105a461-612e-4852-b8f2-f31d0ba79fb0"
204 | },
205 | "source": [
206 | "# printing the first 5 columns of the dataframe\n",
207 | "salary_data.head()"
208 | ],
209 | "execution_count": null,
210 | "outputs": [
211 | {
212 | "output_type": "execute_result",
213 | "data": {
214 | "text/html": [
215 | "\n",
216 | "\n",
229 | "
\n",
230 | " \n",
231 | " \n",
232 | " | \n",
233 | " YearsExperience | \n",
234 | " Salary | \n",
235 | "
\n",
236 | " \n",
237 | " \n",
238 | " \n",
239 | " | 0 | \n",
240 | " 1.1 | \n",
241 | " 39343 | \n",
242 | "
\n",
243 | " \n",
244 | " | 1 | \n",
245 | " 1.3 | \n",
246 | " 46205 | \n",
247 | "
\n",
248 | " \n",
249 | " | 2 | \n",
250 | " 1.5 | \n",
251 | " 37731 | \n",
252 | "
\n",
253 | " \n",
254 | " | 3 | \n",
255 | " 2.0 | \n",
256 | " 43525 | \n",
257 | "
\n",
258 | " \n",
259 | " | 4 | \n",
260 | " 2.2 | \n",
261 | " 39891 | \n",
262 | "
\n",
263 | " \n",
264 | "
\n",
265 | "
\n",
302 | "\n",
315 | "
\n",
316 | " \n",
317 | " \n",
318 | " | \n",
319 | " YearsExperience | \n",
320 | " Salary | \n",
321 | "
\n",
322 | " \n",
323 | " \n",
324 | " \n",
325 | " | 25 | \n",
326 | " 9.0 | \n",
327 | " 105582 | \n",
328 | "
\n",
329 | " \n",
330 | " | 26 | \n",
331 | " 9.5 | \n",
332 | " 116969 | \n",
333 | "
\n",
334 | " \n",
335 | " | 27 | \n",
336 | " 9.6 | \n",
337 | " 112635 | \n",
338 | "
\n",
339 | " \n",
340 | " | 28 | \n",
341 | " 10.3 | \n",
342 | " 122391 | \n",
343 | "
\n",
344 | " \n",
345 | " | 29 | \n",
346 | " 10.5 | \n",
347 | " 121872 | \n",
348 | "
\n",
349 | " \n",
350 | "
\n",
351 | "
"
691 | ]
692 | },
693 | "metadata": {
694 | "needs_background": "light"
695 | }
696 | }
697 | ]
698 | }
699 | ]
700 | }
--------------------------------------------------------------------------------
/7_1_5_Lin_Reg_implementation.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "provenance": [],
7 | "collapsed_sections": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | },
13 | "language_info": {
14 | "name": "python"
15 | }
16 | },
17 | "cells": [
18 | {
19 | "cell_type": "code",
20 | "metadata": {
21 | "id": "-y5S4EZyPYt3"
22 | },
23 | "source": [
24 | "import numpy as np\n",
25 | "import pandas as pd\n",
26 | "from sklearn.model_selection import train_test_split\n",
27 | "import matplotlib.pyplot as plt\n",
28 | "\n",
29 | "import Lin_Reg_model"
30 | ],
31 | "execution_count": null,
32 | "outputs": []
33 | },
34 | {
35 | "cell_type": "markdown",
36 | "metadata": {
37 | "id": "1G3UFDztP9tF"
38 | },
39 | "source": [
40 | "Data Processing"
41 | ]
42 | },
43 | {
44 | "cell_type": "code",
45 | "metadata": {
46 | "id": "YQ4Zx9HbPy1-"
47 | },
48 | "source": [
49 | "# loading the data from csv file to pandas dataframe\n",
50 | "salary_data = pd.read_csv('/content/salary_data.csv')"
51 | ],
52 | "execution_count": null,
53 | "outputs": []
54 | },
55 | {
56 | "cell_type": "code",
57 | "metadata": {
58 | "colab": {
59 | "base_uri": "https://localhost:8080/",
60 | "height": 206
61 | },
62 | "id": "nPfG1QLoQOxU",
63 | "outputId": "e78f6224-777a-4d02-9d93-9a63e62dadb7"
64 | },
65 | "source": [
66 | "# printing the first 5 rows of the dataframe\n",
67 | "salary_data.head()"
68 | ],
69 | "execution_count": null,
70 | "outputs": [
71 | {
72 | "output_type": "execute_result",
73 | "data": {
74 | "text/html": [
75 | "\n",
76 | "\n",
89 | "
\n",
90 | " \n",
91 | " \n",
92 | " | \n",
93 | " YearsExperience | \n",
94 | " Salary | \n",
95 | "
\n",
96 | " \n",
97 | " \n",
98 | " \n",
99 | " | 0 | \n",
100 | " 1.1 | \n",
101 | " 39343 | \n",
102 | "
\n",
103 | " \n",
104 | " | 1 | \n",
105 | " 1.3 | \n",
106 | " 46205 | \n",
107 | "
\n",
108 | " \n",
109 | " | 2 | \n",
110 | " 1.5 | \n",
111 | " 37731 | \n",
112 | "
\n",
113 | " \n",
114 | " | 3 | \n",
115 | " 2.0 | \n",
116 | " 43525 | \n",
117 | "
\n",
118 | " \n",
119 | " | 4 | \n",
120 | " 2.2 | \n",
121 | " 39891 | \n",
122 | "
\n",
123 | " \n",
124 | "
\n",
125 | "
"
454 | ]
455 | },
456 | "metadata": {
457 | "needs_background": "light"
458 | }
459 | }
460 | ]
461 | },
462 | {
463 | "cell_type": "code",
464 | "metadata": {
465 | "id": "ZEgDB1-sV5hr"
466 | },
467 | "source": [],
468 | "execution_count": null,
469 | "outputs": []
470 | }
471 | ]
472 | }
--------------------------------------------------------------------------------
/7_2_5_Building_Logistic_Regression_from_scratch_in_Python.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "provenance": [],
7 | "collapsed_sections": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | },
13 | "language_info": {
14 | "name": "python"
15 | }
16 | },
17 | "cells": [
18 | {
19 | "cell_type": "markdown",
20 | "metadata": {
21 | "id": "f5BLpBB_cv8y"
22 | },
23 | "source": [
24 | "**Logistic Regression:**"
25 | ]
26 | },
27 | {
28 | "cell_type": "markdown",
29 | "metadata": {
30 | "id": "SQA2GUq7cPXd"
31 | },
32 | "source": [
33 | ""
34 | ]
35 | },
36 | {
37 | "cell_type": "markdown",
38 | "metadata": {
39 | "id": "W0dxwE-Ubsdf"
40 | },
41 | "source": [
42 | "Y_hat --> predicted value\n",
43 | "\n",
44 | "X --> Input Variable\n",
45 | "\n",
46 | "w --> weight\n",
47 | "\n",
48 | "b --> bias"
49 | ]
50 | },
51 | {
52 | "cell_type": "markdown",
53 | "metadata": {
54 | "id": "X8OJXGuPvDt2"
55 | },
56 | "source": [
57 | "**Gradient Descent:**\n",
58 | "\n",
59 | "Gradient Descent is an optimization algorithm used for minimizing the loss function in various machine learning algorithms. It is used for updating the parameters of the learning model.\n",
60 | "\n",
61 | "w = w - α*dw\n",
62 | "\n",
63 | "b = b - α*db"
64 | ]
65 | },
66 | {
67 | "cell_type": "markdown",
68 | "metadata": {
69 | "id": "WSAfYP7WmECB"
70 | },
71 | "source": [
72 | "**Learning Rate:**\n",
73 | "\n",
74 | "Learning rate is a tuning parameter in an optimization algorithm that determines the step size at each iteration while moving toward a minimum of a loss function."
75 | ]
76 | },
77 | {
78 | "cell_type": "markdown",
79 | "metadata": {
80 | "id": "s8AfHQz9cXRF"
81 | },
82 | "source": [
83 | "**Derivatives:**"
84 | ]
85 | },
86 | {
87 | "cell_type": "markdown",
88 | "metadata": {
89 | "id": "kLUw3M-WcCwv"
90 | },
91 | "source": [
92 | ""
93 | ]
94 | },
95 | {
96 | "cell_type": "markdown",
97 | "metadata": {
98 | "id": "WxOpuBj_SqV-"
99 | },
100 | "source": [
101 | "Importing the Dependencies"
102 | ]
103 | },
104 | {
105 | "cell_type": "code",
106 | "metadata": {
107 | "id": "fdjRDi8wlgX6"
108 | },
109 | "source": [
110 | "# importing numpy library\n",
111 | "import numpy as np"
112 | ],
113 | "execution_count": null,
114 | "outputs": []
115 | },
116 | {
117 | "cell_type": "markdown",
118 | "metadata": {
119 | "id": "eTA-BwebLjdc"
120 | },
121 | "source": [
122 | "**Logistic Regression**"
123 | ]
124 | },
125 | {
126 | "cell_type": "code",
127 | "metadata": {
128 | "id": "YcqEjNwtKHPq"
129 | },
130 | "source": [
131 | "class Logistic_Regression():\n",
132 | "\n",
133 | "\n",
134 | " # declaring learning rate & number of iterations (Hyperparametes)\n",
135 | " def __init__(self, learning_rate, no_of_iterations):\n",
136 | "\n",
137 | " self.learning_rate = learning_rate\n",
138 | " self.no_of_iterations = no_of_iterations\n",
139 | "\n",
140 | "\n",
141 | "\n",
142 | " # fit function to train the model with dataset\n",
143 | " def fit(self, X, Y):\n",
144 | "\n",
145 | " # number of data points in the dataset (number of rows) --> m\n",
146 | " # number of input features in the dataset (number of columns) --> n\n",
147 | " self.m, self.n = X.shape\n",
148 | "\n",
149 | "\n",
150 | " #initiating weight & bias value\n",
151 | "\n",
152 | " self.w = np.zeros(self.n)\n",
153 | " \n",
154 | " self.b = 0\n",
155 | "\n",
156 | " self.X = X\n",
157 | "\n",
158 | " self.Y = Y\n",
159 | "\n",
160 | "\n",
161 | " # implementing Gradient Descent for Optimization\n",
162 | "\n",
163 | " for i in range(self.no_of_iterations):\n",
164 | " self.update_weights()\n",
165 | "\n",
166 | "\n",
167 | "\n",
168 | " def update_weights(self):\n",
169 | "\n",
170 | " # Y_hat formula (sigmoid function)\n",
171 | "\n",
172 | " Y_hat = 1 / (1 + np.exp( - (self.X.dot(self.w) + self.b ) )) \n",
173 | "\n",
174 | "\n",
175 | " # derivaties\n",
176 | "\n",
177 | " dw = (1/self.m)*np.dot(self.X.T, (Y_hat - self.Y))\n",
178 | "\n",
179 | " db = (1/self.m)*np.sum(Y_hat - self.Y)\n",
180 | "\n",
181 | "\n",
182 | " # updating the weights & bias using gradient descent\n",
183 | "\n",
184 | " self.w = self.w - self.learning_rate * dw\n",
185 | "\n",
186 | " self.b = self.b - self.learning_rate * db\n",
187 | "\n",
188 | "\n",
189 | " # Sigmoid Equation & Decision Boundary\n",
190 | "\n",
191 | " def predict(self, X):\n",
192 | "\n",
193 | " Y_pred = 1 / (1 + np.exp( - (X.dot(self.w) + self.b ) )) \n",
194 | " Y_pred = np.where( Y_pred > 0.5, 1, 0)\n",
195 | " return Y_pred"
196 | ],
197 | "execution_count": null,
198 | "outputs": []
199 | },
200 | {
201 | "cell_type": "code",
202 | "metadata": {
203 | "id": "htiH07T_WL-Y"
204 | },
205 | "source": [],
206 | "execution_count": null,
207 | "outputs": []
208 | }
209 | ]
210 | }
--------------------------------------------------------------------------------
/7_2_6_Logistic_Regression_Implementation.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "provenance": [],
7 | "collapsed_sections": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | },
13 | "language_info": {
14 | "name": "python"
15 | }
16 | },
17 | "cells": [
18 | {
19 | "cell_type": "markdown",
20 | "metadata": {
21 | "id": "LnPbntVRnfvV"
22 | },
23 | "source": [
24 | "Importing the Dependencies"
25 | ]
26 | },
27 | {
28 | "cell_type": "code",
29 | "metadata": {
30 | "id": "-71UtHzNVWjB"
31 | },
32 | "source": [
33 | "import numpy as np\n",
34 | "import pandas as pd\n",
35 | "from sklearn.preprocessing import StandardScaler\n",
36 | "from sklearn.model_selection import train_test_split\n",
37 | "from sklearn.metrics import accuracy_score\n",
38 | "import Log_Reg"
39 | ],
40 | "execution_count": null,
41 | "outputs": []
42 | },
43 | {
44 | "cell_type": "markdown",
45 | "metadata": {
46 | "id": "bmfOfG8joBBy"
47 | },
48 | "source": [
49 | "Data Collection and Analysis\n",
50 | "\n",
51 | "PIMA Diabetes Dataset"
52 | ]
53 | },
54 | {
55 | "cell_type": "code",
56 | "metadata": {
57 | "id": "Xpw6Mj_pn_TL"
58 | },
59 | "source": [
60 | "# loading the diabetes dataset to a pandas DataFrame\n",
61 | "diabetes_dataset = pd.read_csv('/content/diabetes.csv') "
62 | ],
63 | "execution_count": null,
64 | "outputs": []
65 | },
66 | {
67 | "cell_type": "code",
68 | "metadata": {
69 | "colab": {
70 | "base_uri": "https://localhost:8080/",
71 | "height": 203
72 | },
73 | "id": "-tjO09ncovoh",
74 | "outputId": "669a7da3-b683-46d4-f419-31b97847248c"
75 | },
76 | "source": [
77 | "# printing the first 5 rows of the dataset\n",
78 | "diabetes_dataset.head()"
79 | ],
80 | "execution_count": null,
81 | "outputs": [
82 | {
83 | "output_type": "execute_result",
84 | "data": {
85 | "text/html": [
86 | "\n",
87 | "\n",
100 | "
\n",
101 | " \n",
102 | " \n",
103 | " | \n",
104 | " Pregnancies | \n",
105 | " Glucose | \n",
106 | " BloodPressure | \n",
107 | " SkinThickness | \n",
108 | " Insulin | \n",
109 | " BMI | \n",
110 | " DiabetesPedigreeFunction | \n",
111 | " Age | \n",
112 | " Outcome | \n",
113 | "
\n",
114 | " \n",
115 | " \n",
116 | " \n",
117 | " | 0 | \n",
118 | " 6 | \n",
119 | " 148 | \n",
120 | " 72 | \n",
121 | " 35 | \n",
122 | " 0 | \n",
123 | " 33.6 | \n",
124 | " 0.627 | \n",
125 | " 50 | \n",
126 | " 1 | \n",
127 | "
\n",
128 | " \n",
129 | " | 1 | \n",
130 | " 1 | \n",
131 | " 85 | \n",
132 | " 66 | \n",
133 | " 29 | \n",
134 | " 0 | \n",
135 | " 26.6 | \n",
136 | " 0.351 | \n",
137 | " 31 | \n",
138 | " 0 | \n",
139 | "
\n",
140 | " \n",
141 | " | 2 | \n",
142 | " 8 | \n",
143 | " 183 | \n",
144 | " 64 | \n",
145 | " 0 | \n",
146 | " 0 | \n",
147 | " 23.3 | \n",
148 | " 0.672 | \n",
149 | " 32 | \n",
150 | " 1 | \n",
151 | "
\n",
152 | " \n",
153 | " | 3 | \n",
154 | " 1 | \n",
155 | " 89 | \n",
156 | " 66 | \n",
157 | " 23 | \n",
158 | " 94 | \n",
159 | " 28.1 | \n",
160 | " 0.167 | \n",
161 | " 21 | \n",
162 | " 0 | \n",
163 | "
\n",
164 | " \n",
165 | " | 4 | \n",
166 | " 0 | \n",
167 | " 137 | \n",
168 | " 40 | \n",
169 | " 35 | \n",
170 | " 168 | \n",
171 | " 43.1 | \n",
172 | " 2.288 | \n",
173 | " 33 | \n",
174 | " 1 | \n",
175 | "
\n",
176 | " \n",
177 | "
\n",
178 | "
\n",
244 | "\n",
257 | "
\n",
258 | " \n",
259 | " \n",
260 | " | \n",
261 | " Pregnancies | \n",
262 | " Glucose | \n",
263 | " BloodPressure | \n",
264 | " SkinThickness | \n",
265 | " Insulin | \n",
266 | " BMI | \n",
267 | " DiabetesPedigreeFunction | \n",
268 | " Age | \n",
269 | " Outcome | \n",
270 | "
\n",
271 | " \n",
272 | " \n",
273 | " \n",
274 | " | count | \n",
275 | " 768.000000 | \n",
276 | " 768.000000 | \n",
277 | " 768.000000 | \n",
278 | " 768.000000 | \n",
279 | " 768.000000 | \n",
280 | " 768.000000 | \n",
281 | " 768.000000 | \n",
282 | " 768.000000 | \n",
283 | " 768.000000 | \n",
284 | "
\n",
285 | " \n",
286 | " | mean | \n",
287 | " 3.845052 | \n",
288 | " 120.894531 | \n",
289 | " 69.105469 | \n",
290 | " 20.536458 | \n",
291 | " 79.799479 | \n",
292 | " 31.992578 | \n",
293 | " 0.471876 | \n",
294 | " 33.240885 | \n",
295 | " 0.348958 | \n",
296 | "
\n",
297 | " \n",
298 | " | std | \n",
299 | " 3.369578 | \n",
300 | " 31.972618 | \n",
301 | " 19.355807 | \n",
302 | " 15.952218 | \n",
303 | " 115.244002 | \n",
304 | " 7.884160 | \n",
305 | " 0.331329 | \n",
306 | " 11.760232 | \n",
307 | " 0.476951 | \n",
308 | "
\n",
309 | " \n",
310 | " | min | \n",
311 | " 0.000000 | \n",
312 | " 0.000000 | \n",
313 | " 0.000000 | \n",
314 | " 0.000000 | \n",
315 | " 0.000000 | \n",
316 | " 0.000000 | \n",
317 | " 0.078000 | \n",
318 | " 21.000000 | \n",
319 | " 0.000000 | \n",
320 | "
\n",
321 | " \n",
322 | " | 25% | \n",
323 | " 1.000000 | \n",
324 | " 99.000000 | \n",
325 | " 62.000000 | \n",
326 | " 0.000000 | \n",
327 | " 0.000000 | \n",
328 | " 27.300000 | \n",
329 | " 0.243750 | \n",
330 | " 24.000000 | \n",
331 | " 0.000000 | \n",
332 | "
\n",
333 | " \n",
334 | " | 50% | \n",
335 | " 3.000000 | \n",
336 | " 117.000000 | \n",
337 | " 72.000000 | \n",
338 | " 23.000000 | \n",
339 | " 30.500000 | \n",
340 | " 32.000000 | \n",
341 | " 0.372500 | \n",
342 | " 29.000000 | \n",
343 | " 0.000000 | \n",
344 | "
\n",
345 | " \n",
346 | " | 75% | \n",
347 | " 6.000000 | \n",
348 | " 140.250000 | \n",
349 | " 80.000000 | \n",
350 | " 32.000000 | \n",
351 | " 127.250000 | \n",
352 | " 36.600000 | \n",
353 | " 0.626250 | \n",
354 | " 41.000000 | \n",
355 | " 1.000000 | \n",
356 | "
\n",
357 | " \n",
358 | " | max | \n",
359 | " 17.000000 | \n",
360 | " 199.000000 | \n",
361 | " 122.000000 | \n",
362 | " 99.000000 | \n",
363 | " 846.000000 | \n",
364 | " 67.100000 | \n",
365 | " 2.420000 | \n",
366 | " 81.000000 | \n",
367 | " 1.000000 | \n",
368 | "
\n",
369 | " \n",
370 | "
\n",
371 | "
\n",
451 | "\n",
464 | "
\n",
465 | " \n",
466 | " \n",
467 | " | \n",
468 | " Pregnancies | \n",
469 | " Glucose | \n",
470 | " BloodPressure | \n",
471 | " SkinThickness | \n",
472 | " Insulin | \n",
473 | " BMI | \n",
474 | " DiabetesPedigreeFunction | \n",
475 | " Age | \n",
476 | "
\n",
477 | " \n",
478 | " | Outcome | \n",
479 | " | \n",
480 | " | \n",
481 | " | \n",
482 | " | \n",
483 | " | \n",
484 | " | \n",
485 | " | \n",
486 | " | \n",
487 | "
\n",
488 | " \n",
489 | " \n",
490 | " \n",
491 | " | 0 | \n",
492 | " 3.298000 | \n",
493 | " 109.980000 | \n",
494 | " 68.184000 | \n",
495 | " 19.664000 | \n",
496 | " 68.792000 | \n",
497 | " 30.304200 | \n",
498 | " 0.429734 | \n",
499 | " 31.190000 | \n",
500 | "
\n",
501 | " \n",
502 | " | 1 | \n",
503 | " 4.865672 | \n",
504 | " 141.257463 | \n",
505 | " 70.824627 | \n",
506 | " 22.164179 | \n",
507 | " 100.335821 | \n",
508 | " 35.142537 | \n",
509 | " 0.550500 | \n",
510 | " 37.067164 | \n",
511 | "
\n",
512 | " \n",
513 | "
\n",
514 | "
\n",
246 | "\n",
259 | "
\n",
260 | " \n",
261 | " \n",
262 | " | \n",
263 | " Pregnancies | \n",
264 | " Glucose | \n",
265 | " BloodPressure | \n",
266 | " SkinThickness | \n",
267 | " Insulin | \n",
268 | " BMI | \n",
269 | " DiabetesPedigreeFunction | \n",
270 | " Age | \n",
271 | " Outcome | \n",
272 | "
\n",
273 | " \n",
274 | " \n",
275 | " \n",
276 | " | 0 | \n",
277 | " 6 | \n",
278 | " 148 | \n",
279 | " 72 | \n",
280 | " 35 | \n",
281 | " 0 | \n",
282 | " 33.6 | \n",
283 | " 0.627 | \n",
284 | " 50 | \n",
285 | " 1 | \n",
286 | "
\n",
287 | " \n",
288 | " | 1 | \n",
289 | " 1 | \n",
290 | " 85 | \n",
291 | " 66 | \n",
292 | " 29 | \n",
293 | " 0 | \n",
294 | " 26.6 | \n",
295 | " 0.351 | \n",
296 | " 31 | \n",
297 | " 0 | \n",
298 | "
\n",
299 | " \n",
300 | " | 2 | \n",
301 | " 8 | \n",
302 | " 183 | \n",
303 | " 64 | \n",
304 | " 0 | \n",
305 | " 0 | \n",
306 | " 23.3 | \n",
307 | " 0.672 | \n",
308 | " 32 | \n",
309 | " 1 | \n",
310 | "
\n",
311 | " \n",
312 | " | 3 | \n",
313 | " 1 | \n",
314 | " 89 | \n",
315 | " 66 | \n",
316 | " 23 | \n",
317 | " 94 | \n",
318 | " 28.1 | \n",
319 | " 0.167 | \n",
320 | " 21 | \n",
321 | " 0 | \n",
322 | "
\n",
323 | " \n",
324 | " | 4 | \n",
325 | " 0 | \n",
326 | " 137 | \n",
327 | " 40 | \n",
328 | " 35 | \n",
329 | " 168 | \n",
330 | " 43.1 | \n",
331 | " 2.288 | \n",
332 | " 33 | \n",
333 | " 1 | \n",
334 | "
\n",
335 | " \n",
336 | "
\n",
337 | "
\n",
403 | "\n",
416 | "
\n",
417 | " \n",
418 | " \n",
419 | " | \n",
420 | " Pregnancies | \n",
421 | " Glucose | \n",
422 | " BloodPressure | \n",
423 | " SkinThickness | \n",
424 | " Insulin | \n",
425 | " BMI | \n",
426 | " DiabetesPedigreeFunction | \n",
427 | " Age | \n",
428 | " Outcome | \n",
429 | "
\n",
430 | " \n",
431 | " \n",
432 | " \n",
433 | " | count | \n",
434 | " 768.000000 | \n",
435 | " 768.000000 | \n",
436 | " 768.000000 | \n",
437 | " 768.000000 | \n",
438 | " 768.000000 | \n",
439 | " 768.000000 | \n",
440 | " 768.000000 | \n",
441 | " 768.000000 | \n",
442 | " 768.000000 | \n",
443 | "
\n",
444 | " \n",
445 | " | mean | \n",
446 | " 3.845052 | \n",
447 | " 120.894531 | \n",
448 | " 69.105469 | \n",
449 | " 20.536458 | \n",
450 | " 79.799479 | \n",
451 | " 31.992578 | \n",
452 | " 0.471876 | \n",
453 | " 33.240885 | \n",
454 | " 0.348958 | \n",
455 | "
\n",
456 | " \n",
457 | " | std | \n",
458 | " 3.369578 | \n",
459 | " 31.972618 | \n",
460 | " 19.355807 | \n",
461 | " 15.952218 | \n",
462 | " 115.244002 | \n",
463 | " 7.884160 | \n",
464 | " 0.331329 | \n",
465 | " 11.760232 | \n",
466 | " 0.476951 | \n",
467 | "
\n",
468 | " \n",
469 | " | min | \n",
470 | " 0.000000 | \n",
471 | " 0.000000 | \n",
472 | " 0.000000 | \n",
473 | " 0.000000 | \n",
474 | " 0.000000 | \n",
475 | " 0.000000 | \n",
476 | " 0.078000 | \n",
477 | " 21.000000 | \n",
478 | " 0.000000 | \n",
479 | "
\n",
480 | " \n",
481 | " | 25% | \n",
482 | " 1.000000 | \n",
483 | " 99.000000 | \n",
484 | " 62.000000 | \n",
485 | " 0.000000 | \n",
486 | " 0.000000 | \n",
487 | " 27.300000 | \n",
488 | " 0.243750 | \n",
489 | " 24.000000 | \n",
490 | " 0.000000 | \n",
491 | "
\n",
492 | " \n",
493 | " | 50% | \n",
494 | " 3.000000 | \n",
495 | " 117.000000 | \n",
496 | " 72.000000 | \n",
497 | " 23.000000 | \n",
498 | " 30.500000 | \n",
499 | " 32.000000 | \n",
500 | " 0.372500 | \n",
501 | " 29.000000 | \n",
502 | " 0.000000 | \n",
503 | "
\n",
504 | " \n",
505 | " | 75% | \n",
506 | " 6.000000 | \n",
507 | " 140.250000 | \n",
508 | " 80.000000 | \n",
509 | " 32.000000 | \n",
510 | " 127.250000 | \n",
511 | " 36.600000 | \n",
512 | " 0.626250 | \n",
513 | " 41.000000 | \n",
514 | " 1.000000 | \n",
515 | "
\n",
516 | " \n",
517 | " | max | \n",
518 | " 17.000000 | \n",
519 | " 199.000000 | \n",
520 | " 122.000000 | \n",
521 | " 99.000000 | \n",
522 | " 846.000000 | \n",
523 | " 67.100000 | \n",
524 | " 2.420000 | \n",
525 | " 81.000000 | \n",
526 | " 1.000000 | \n",
527 | "
\n",
528 | " \n",
529 | "
\n",
530 | "
\n",
88 | "\n",
101 | "
\n",
102 | " \n",
103 | " \n",
104 | " | \n",
105 | " Pregnancies | \n",
106 | " Glucose | \n",
107 | " BloodPressure | \n",
108 | " SkinThickness | \n",
109 | " Insulin | \n",
110 | " BMI | \n",
111 | " DiabetesPedigreeFunction | \n",
112 | " Age | \n",
113 | " Outcome | \n",
114 | "
\n",
115 | " \n",
116 | " \n",
117 | " \n",
118 | " | 0 | \n",
119 | " 6 | \n",
120 | " 148 | \n",
121 | " 72 | \n",
122 | " 35 | \n",
123 | " 0 | \n",
124 | " 33.6 | \n",
125 | " 0.627 | \n",
126 | " 50 | \n",
127 | " 1 | \n",
128 | "
\n",
129 | " \n",
130 | " | 1 | \n",
131 | " 1 | \n",
132 | " 85 | \n",
133 | " 66 | \n",
134 | " 29 | \n",
135 | " 0 | \n",
136 | " 26.6 | \n",
137 | " 0.351 | \n",
138 | " 31 | \n",
139 | " 0 | \n",
140 | "
\n",
141 | " \n",
142 | " | 2 | \n",
143 | " 8 | \n",
144 | " 183 | \n",
145 | " 64 | \n",
146 | " 0 | \n",
147 | " 0 | \n",
148 | " 23.3 | \n",
149 | " 0.672 | \n",
150 | " 32 | \n",
151 | " 1 | \n",
152 | "
\n",
153 | " \n",
154 | " | 3 | \n",
155 | " 1 | \n",
156 | " 89 | \n",
157 | " 66 | \n",
158 | " 23 | \n",
159 | " 94 | \n",
160 | " 28.1 | \n",
161 | " 0.167 | \n",
162 | " 21 | \n",
163 | " 0 | \n",
164 | "
\n",
165 | " \n",
166 | " | 4 | \n",
167 | " 0 | \n",
168 | " 137 | \n",
169 | " 40 | \n",
170 | " 35 | \n",
171 | " 168 | \n",
172 | " 43.1 | \n",
173 | " 2.288 | \n",
174 | " 33 | \n",
175 | " 1 | \n",
176 | "
\n",
177 | " \n",
178 | "
\n",
179 | "
\n",
245 | "\n",
258 | "
\n",
259 | " \n",
260 | " \n",
261 | " | \n",
262 | " Pregnancies | \n",
263 | " Glucose | \n",
264 | " BloodPressure | \n",
265 | " SkinThickness | \n",
266 | " Insulin | \n",
267 | " BMI | \n",
268 | " DiabetesPedigreeFunction | \n",
269 | " Age | \n",
270 | " Outcome | \n",
271 | "
\n",
272 | " \n",
273 | " \n",
274 | " \n",
275 | " | count | \n",
276 | " 768.000000 | \n",
277 | " 768.000000 | \n",
278 | " 768.000000 | \n",
279 | " 768.000000 | \n",
280 | " 768.000000 | \n",
281 | " 768.000000 | \n",
282 | " 768.000000 | \n",
283 | " 768.000000 | \n",
284 | " 768.000000 | \n",
285 | "
\n",
286 | " \n",
287 | " | mean | \n",
288 | " 3.845052 | \n",
289 | " 120.894531 | \n",
290 | " 69.105469 | \n",
291 | " 20.536458 | \n",
292 | " 79.799479 | \n",
293 | " 31.992578 | \n",
294 | " 0.471876 | \n",
295 | " 33.240885 | \n",
296 | " 0.348958 | \n",
297 | "
\n",
298 | " \n",
299 | " | std | \n",
300 | " 3.369578 | \n",
301 | " 31.972618 | \n",
302 | " 19.355807 | \n",
303 | " 15.952218 | \n",
304 | " 115.244002 | \n",
305 | " 7.884160 | \n",
306 | " 0.331329 | \n",
307 | " 11.760232 | \n",
308 | " 0.476951 | \n",
309 | "
\n",
310 | " \n",
311 | " | min | \n",
312 | " 0.000000 | \n",
313 | " 0.000000 | \n",
314 | " 0.000000 | \n",
315 | " 0.000000 | \n",
316 | " 0.000000 | \n",
317 | " 0.000000 | \n",
318 | " 0.078000 | \n",
319 | " 21.000000 | \n",
320 | " 0.000000 | \n",
321 | "
\n",
322 | " \n",
323 | " | 25% | \n",
324 | " 1.000000 | \n",
325 | " 99.000000 | \n",
326 | " 62.000000 | \n",
327 | " 0.000000 | \n",
328 | " 0.000000 | \n",
329 | " 27.300000 | \n",
330 | " 0.243750 | \n",
331 | " 24.000000 | \n",
332 | " 0.000000 | \n",
333 | "
\n",
334 | " \n",
335 | " | 50% | \n",
336 | " 3.000000 | \n",
337 | " 117.000000 | \n",
338 | " 72.000000 | \n",
339 | " 23.000000 | \n",
340 | " 30.500000 | \n",
341 | " 32.000000 | \n",
342 | " 0.372500 | \n",
343 | " 29.000000 | \n",
344 | " 0.000000 | \n",
345 | "
\n",
346 | " \n",
347 | " | 75% | \n",
348 | " 6.000000 | \n",
349 | " 140.250000 | \n",
350 | " 80.000000 | \n",
351 | " 32.000000 | \n",
352 | " 127.250000 | \n",
353 | " 36.600000 | \n",
354 | " 0.626250 | \n",
355 | " 41.000000 | \n",
356 | " 1.000000 | \n",
357 | "
\n",
358 | " \n",
359 | " | max | \n",
360 | " 17.000000 | \n",
361 | " 199.000000 | \n",
362 | " 122.000000 | \n",
363 | " 99.000000 | \n",
364 | " 846.000000 | \n",
365 | " 67.100000 | \n",
366 | " 2.420000 | \n",
367 | " 81.000000 | \n",
368 | " 1.000000 | \n",
369 | "
\n",
370 | " \n",
371 | "
\n",
372 | "
\n",
452 | "\n",
465 | "
\n",
466 | " \n",
467 | " \n",
468 | " | \n",
469 | " Pregnancies | \n",
470 | " Glucose | \n",
471 | " BloodPressure | \n",
472 | " SkinThickness | \n",
473 | " Insulin | \n",
474 | " BMI | \n",
475 | " DiabetesPedigreeFunction | \n",
476 | " Age | \n",
477 | "
\n",
478 | " \n",
479 | " | Outcome | \n",
480 | " | \n",
481 | " | \n",
482 | " | \n",
483 | " | \n",
484 | " | \n",
485 | " | \n",
486 | " | \n",
487 | " | \n",
488 | "
\n",
489 | " \n",
490 | " \n",
491 | " \n",
492 | " | 0 | \n",
493 | " 3.298000 | \n",
494 | " 109.980000 | \n",
495 | " 68.184000 | \n",
496 | " 19.664000 | \n",
497 | " 68.792000 | \n",
498 | " 30.304200 | \n",
499 | " 0.429734 | \n",
500 | " 31.190000 | \n",
501 | "
\n",
502 | " \n",
503 | " | 1 | \n",
504 | " 4.865672 | \n",
505 | " 141.257463 | \n",
506 | " 70.824627 | \n",
507 | " 22.164179 | \n",
508 | " 100.335821 | \n",
509 | " 35.142537 | \n",
510 | " 0.550500 | \n",
511 | " 37.067164 | \n",
512 | "
\n",
513 | " \n",
514 | "
\n",
515 | "