Skip to content

Commit b4c1e86

Browse files
jaydipkumarjaydipkumar
authored
Add files via upload
1 parent 33568c2 commit b4c1e86

File tree

1 file changed

+316
-0
lines changed

1 file changed

+316
-0
lines changed

‎Random Forest Classification.ipynb

+316
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,316 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"metadata": {},
7+
"outputs": [],
8+
"source": [
9+
"#import libabry\n",
10+
"import pandas as pd\n",
11+
"from sklearn.model_selection import train_test_split\n",
12+
"from sklearn.ensemble import RandomForestClassifier\n",
13+
"from sklearn import metrics"
14+
]
15+
},
16+
{
17+
"cell_type": "code",
18+
"execution_count": 2,
19+
"metadata": {},
20+
"outputs": [],
21+
"source": [
22+
"#import dataset\n",
23+
"Diabetes = pd.read_csv('~/Downloads/Data Science/data set/Diabetes.csv') "
24+
]
25+
},
26+
{
27+
"cell_type": "code",
28+
"execution_count": 3,
29+
"metadata": {},
30+
"outputs": [
31+
{
32+
"data": {
33+
"text/html": [
34+
"<div>\n",
35+
"<style scoped>\n",
36+
" .dataframe tbody tr th:only-of-type {\n",
37+
" vertical-align: middle;\n",
38+
" }\n",
39+
"\n",
40+
" .dataframe tbody tr th {\n",
41+
" vertical-align: top;\n",
42+
" }\n",
43+
"\n",
44+
" .dataframe thead th {\n",
45+
" text-align: right;\n",
46+
" }\n",
47+
"</style>\n",
48+
"<table border=\"1\" class=\"dataframe\">\n",
49+
" <thead>\n",
50+
" <tr style=\"text-align: right;\">\n",
51+
" <th></th>\n",
52+
" <th>Pregnancies</th>\n",
53+
" <th>Glucose</th>\n",
54+
" <th>BloodPressure</th>\n",
55+
" <th>SkinThickness</th>\n",
56+
" <th>Insulin</th>\n",
57+
" <th>BMI</th>\n",
58+
" <th>DiabetesPedigreeFunction</th>\n",
59+
" <th>Age</th>\n",
60+
" <th>Outcome</th>\n",
61+
" </tr>\n",
62+
" </thead>\n",
63+
" <tbody>\n",
64+
" <tr>\n",
65+
" <th>0</th>\n",
66+
" <td>6</td>\n",
67+
" <td>148</td>\n",
68+
" <td>72</td>\n",
69+
" <td>35</td>\n",
70+
" <td>0</td>\n",
71+
" <td>33.6</td>\n",
72+
" <td>0.627</td>\n",
73+
" <td>50</td>\n",
74+
" <td>1</td>\n",
75+
" </tr>\n",
76+
" <tr>\n",
77+
" <th>1</th>\n",
78+
" <td>1</td>\n",
79+
" <td>85</td>\n",
80+
" <td>66</td>\n",
81+
" <td>29</td>\n",
82+
" <td>0</td>\n",
83+
" <td>26.6</td>\n",
84+
" <td>0.351</td>\n",
85+
" <td>31</td>\n",
86+
" <td>0</td>\n",
87+
" </tr>\n",
88+
" <tr>\n",
89+
" <th>2</th>\n",
90+
" <td>8</td>\n",
91+
" <td>183</td>\n",
92+
" <td>64</td>\n",
93+
" <td>0</td>\n",
94+
" <td>0</td>\n",
95+
" <td>23.3</td>\n",
96+
" <td>0.672</td>\n",
97+
" <td>32</td>\n",
98+
" <td>1</td>\n",
99+
" </tr>\n",
100+
" <tr>\n",
101+
" <th>3</th>\n",
102+
" <td>1</td>\n",
103+
" <td>89</td>\n",
104+
" <td>66</td>\n",
105+
" <td>23</td>\n",
106+
" <td>94</td>\n",
107+
" <td>28.1</td>\n",
108+
" <td>0.167</td>\n",
109+
" <td>21</td>\n",
110+
" <td>0</td>\n",
111+
" </tr>\n",
112+
" <tr>\n",
113+
" <th>4</th>\n",
114+
" <td>0</td>\n",
115+
" <td>137</td>\n",
116+
" <td>40</td>\n",
117+
" <td>35</td>\n",
118+
" <td>168</td>\n",
119+
" <td>43.1</td>\n",
120+
" <td>2.288</td>\n",
121+
" <td>33</td>\n",
122+
" <td>1</td>\n",
123+
" </tr>\n",
124+
" <tr>\n",
125+
" <th>...</th>\n",
126+
" <td>...</td>\n",
127+
" <td>...</td>\n",
128+
" <td>...</td>\n",
129+
" <td>...</td>\n",
130+
" <td>...</td>\n",
131+
" <td>...</td>\n",
132+
" <td>...</td>\n",
133+
" <td>...</td>\n",
134+
" <td>...</td>\n",
135+
" </tr>\n",
136+
" <tr>\n",
137+
" <th>763</th>\n",
138+
" <td>10</td>\n",
139+
" <td>101</td>\n",
140+
" <td>76</td>\n",
141+
" <td>48</td>\n",
142+
" <td>180</td>\n",
143+
" <td>32.9</td>\n",
144+
" <td>0.171</td>\n",
145+
" <td>63</td>\n",
146+
" <td>0</td>\n",
147+
" </tr>\n",
148+
" <tr>\n",
149+
" <th>764</th>\n",
150+
" <td>2</td>\n",
151+
" <td>122</td>\n",
152+
" <td>70</td>\n",
153+
" <td>27</td>\n",
154+
" <td>0</td>\n",
155+
" <td>36.8</td>\n",
156+
" <td>0.340</td>\n",
157+
" <td>27</td>\n",
158+
" <td>0</td>\n",
159+
" </tr>\n",
160+
" <tr>\n",
161+
" <th>765</th>\n",
162+
" <td>5</td>\n",
163+
" <td>121</td>\n",
164+
" <td>72</td>\n",
165+
" <td>23</td>\n",
166+
" <td>112</td>\n",
167+
" <td>26.2</td>\n",
168+
" <td>0.245</td>\n",
169+
" <td>30</td>\n",
170+
" <td>0</td>\n",
171+
" </tr>\n",
172+
" <tr>\n",
173+
" <th>766</th>\n",
174+
" <td>1</td>\n",
175+
" <td>126</td>\n",
176+
" <td>60</td>\n",
177+
" <td>0</td>\n",
178+
" <td>0</td>\n",
179+
" <td>30.1</td>\n",
180+
" <td>0.349</td>\n",
181+
" <td>47</td>\n",
182+
" <td>1</td>\n",
183+
" </tr>\n",
184+
" <tr>\n",
185+
" <th>767</th>\n",
186+
" <td>1</td>\n",
187+
" <td>93</td>\n",
188+
" <td>70</td>\n",
189+
" <td>31</td>\n",
190+
" <td>0</td>\n",
191+
" <td>30.4</td>\n",
192+
" <td>0.315</td>\n",
193+
" <td>23</td>\n",
194+
" <td>0</td>\n",
195+
" </tr>\n",
196+
" </tbody>\n",
197+
"</table>\n",
198+
"<p>768 rows × 9 columns</p>\n",
199+
"</div>"
200+
],
201+
"text/plain": [
202+
" Pregnancies Glucose BloodPressure SkinThickness Insulin BMI \\\n",
203+
"0 6 148 72 35 0 33.6 \n",
204+
"1 1 85 66 29 0 26.6 \n",
205+
"2 8 183 64 0 0 23.3 \n",
206+
"3 1 89 66 23 94 28.1 \n",
207+
"4 0 137 40 35 168 43.1 \n",
208+
".. ... ... ... ... ... ... \n",
209+
"763 10 101 76 48 180 32.9 \n",
210+
"764 2 122 70 27 0 36.8 \n",
211+
"765 5 121 72 23 112 26.2 \n",
212+
"766 1 126 60 0 0 30.1 \n",
213+
"767 1 93 70 31 0 30.4 \n",
214+
"\n",
215+
" DiabetesPedigreeFunction Age Outcome \n",
216+
"0 0.627 50 1 \n",
217+
"1 0.351 31 0 \n",
218+
"2 0.672 32 1 \n",
219+
"3 0.167 21 0 \n",
220+
"4 2.288 33 1 \n",
221+
".. ... ... ... \n",
222+
"763 0.171 63 0 \n",
223+
"764 0.340 27 0 \n",
224+
"765 0.245 30 0 \n",
225+
"766 0.349 47 1 \n",
226+
"767 0.315 23 0 \n",
227+
"\n",
228+
"[768 rows x 9 columns]"
229+
]
230+
},
231+
"execution_count": 3,
232+
"metadata": {},
233+
"output_type": "execute_result"
234+
}
235+
],
236+
"source": [
237+
"Diabetes"
238+
]
239+
},
240+
{
241+
"cell_type": "code",
242+
"execution_count": 4,
243+
"metadata": {},
244+
"outputs": [],
245+
"source": [
246+
"colnames = list(Diabetes.columns)\n",
247+
"predictors = colnames[:8]\n",
248+
"target = colnames[8]"
249+
]
250+
},
251+
{
252+
"cell_type": "code",
253+
"execution_count": 5,
254+
"metadata": {},
255+
"outputs": [],
256+
"source": [
257+
"# Split dataset\n",
258+
"X_train, X_test, y_train, y_test = train_test_split(Diabetes[predictors],Diabetes[target],test_size=0.3, random_state=0)"
259+
]
260+
},
261+
{
262+
"cell_type": "code",
263+
"execution_count": 6,
264+
"metadata": {},
265+
"outputs": [],
266+
"source": [
267+
"#Create a Gaussian Classifier\n",
268+
"clf=RandomForestClassifier(n_estimators=100)\n",
269+
"\n",
270+
"#Train the model using the training\n",
271+
"clf.fit(X_train,y_train)\n",
272+
"\n",
273+
"y_pred=clf.predict(X_test)"
274+
]
275+
},
276+
{
277+
"cell_type": "code",
278+
"execution_count": 7,
279+
"metadata": {},
280+
"outputs": [
281+
{
282+
"name": "stdout",
283+
"output_type": "stream",
284+
"text": [
285+
"Accuracy: 0.7575757575757576\n"
286+
]
287+
}
288+
],
289+
"source": [
290+
"# Model Accuracy\n",
291+
"print(\"Accuracy:\",metrics.accuracy_score(y_test, y_pred))"
292+
]
293+
}
294+
],
295+
"metadata": {
296+
"kernelspec": {
297+
"display_name": "Python 3",
298+
"language": "python",
299+
"name": "python3"
300+
},
301+
"language_info": {
302+
"codemirror_mode": {
303+
"name": "ipython",
304+
"version": 3
305+
},
306+
"file_extension": ".py",
307+
"mimetype": "text/x-python",
308+
"name": "python",
309+
"nbconvert_exporter": "python",
310+
"pygments_lexer": "ipython3",
311+
"version": "3.6.8"
312+
}
313+
},
314+
"nbformat": 4,
315+
"nbformat_minor": 4
316+
}

0 commit comments

Comments
 (0)