Skip to content

Commit 9986358

Browse files
jaydipkumarjaydipkumar
authored
Add files via upload
1 parent dfbb066 commit 9986358

File tree

1 file changed

+320
-0
lines changed

1 file changed

+320
-0
lines changed

‎Random Forest Classification.ipynb

Lines changed: 320 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,320 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 2,
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\n",
14+
"from sklearn.ensemble import RandomForestClassifier"
15+
]
16+
},
17+
{
18+
"cell_type": "code",
19+
"execution_count": 3,
20+
"metadata": {},
21+
"outputs": [],
22+
"source": [
23+
"#import dataset\n",
24+
"Diabetes = pd.read_csv('~/Downloads/Data Science/data set/Diabetes.csv') "
25+
]
26+
},
27+
{
28+
"cell_type": "code",
29+
"execution_count": 4,
30+
"metadata": {},
31+
"outputs": [
32+
{
33+
"data": {
34+
"text/html": [
35+
"<div>\n",
36+
"<style scoped>\n",
37+
" .dataframe tbody tr th:only-of-type {\n",
38+
" vertical-align: middle;\n",
39+
" }\n",
40+
"\n",
41+
" .dataframe tbody tr th {\n",
42+
" vertical-align: top;\n",
43+
" }\n",
44+
"\n",
45+
" .dataframe thead th {\n",
46+
" text-align: right;\n",
47+
" }\n",
48+
"</style>\n",
49+
"<table border=\"1\" class=\"dataframe\">\n",
50+
" <thead>\n",
51+
" <tr style=\"text-align: right;\">\n",
52+
" <th></th>\n",
53+
" <th>Pregnancies</th>\n",
54+
" <th>Glucose</th>\n",
55+
" <th>BloodPressure</th>\n",
56+
" <th>SkinThickness</th>\n",
57+
" <th>Insulin</th>\n",
58+
" <th>BMI</th>\n",
59+
" <th>DiabetesPedigreeFunction</th>\n",
60+
" <th>Age</th>\n",
61+
" <th>Outcome</th>\n",
62+
" </tr>\n",
63+
" </thead>\n",
64+
" <tbody>\n",
65+
" <tr>\n",
66+
" <th>0</th>\n",
67+
" <td>6</td>\n",
68+
" <td>148</td>\n",
69+
" <td>72</td>\n",
70+
" <td>35</td>\n",
71+
" <td>0</td>\n",
72+
" <td>33.6</td>\n",
73+
" <td>0.627</td>\n",
74+
" <td>50</td>\n",
75+
" <td>1</td>\n",
76+
" </tr>\n",
77+
" <tr>\n",
78+
" <th>1</th>\n",
79+
" <td>1</td>\n",
80+
" <td>85</td>\n",
81+
" <td>66</td>\n",
82+
" <td>29</td>\n",
83+
" <td>0</td>\n",
84+
" <td>26.6</td>\n",
85+
" <td>0.351</td>\n",
86+
" <td>31</td>\n",
87+
" <td>0</td>\n",
88+
" </tr>\n",
89+
" <tr>\n",
90+
" <th>2</th>\n",
91+
" <td>8</td>\n",
92+
" <td>183</td>\n",
93+
" <td>64</td>\n",
94+
" <td>0</td>\n",
95+
" <td>0</td>\n",
96+
" <td>23.3</td>\n",
97+
" <td>0.672</td>\n",
98+
" <td>32</td>\n",
99+
" <td>1</td>\n",
100+
" </tr>\n",
101+
" <tr>\n",
102+
" <th>3</th>\n",
103+
" <td>1</td>\n",
104+
" <td>89</td>\n",
105+
" <td>66</td>\n",
106+
" <td>23</td>\n",
107+
" <td>94</td>\n",
108+
" <td>28.1</td>\n",
109+
" <td>0.167</td>\n",
110+
" <td>21</td>\n",
111+
" <td>0</td>\n",
112+
" </tr>\n",
113+
" <tr>\n",
114+
" <th>4</th>\n",
115+
" <td>0</td>\n",
116+
" <td>137</td>\n",
117+
" <td>40</td>\n",
118+
" <td>35</td>\n",
119+
" <td>168</td>\n",
120+
" <td>43.1</td>\n",
121+
" <td>2.288</td>\n",
122+
" <td>33</td>\n",
123+
" <td>1</td>\n",
124+
" </tr>\n",
125+
" <tr>\n",
126+
" <th>...</th>\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+
" <td>...</td>\n",
136+
" </tr>\n",
137+
" <tr>\n",
138+
" <th>763</th>\n",
139+
" <td>10</td>\n",
140+
" <td>101</td>\n",
141+
" <td>76</td>\n",
142+
" <td>48</td>\n",
143+
" <td>180</td>\n",
144+
" <td>32.9</td>\n",
145+
" <td>0.171</td>\n",
146+
" <td>63</td>\n",
147+
" <td>0</td>\n",
148+
" </tr>\n",
149+
" <tr>\n",
150+
" <th>764</th>\n",
151+
" <td>2</td>\n",
152+
" <td>122</td>\n",
153+
" <td>70</td>\n",
154+
" <td>27</td>\n",
155+
" <td>0</td>\n",
156+
" <td>36.8</td>\n",
157+
" <td>0.340</td>\n",
158+
" <td>27</td>\n",
159+
" <td>0</td>\n",
160+
" </tr>\n",
161+
" <tr>\n",
162+
" <th>765</th>\n",
163+
" <td>5</td>\n",
164+
" <td>121</td>\n",
165+
" <td>72</td>\n",
166+
" <td>23</td>\n",
167+
" <td>112</td>\n",
168+
" <td>26.2</td>\n",
169+
" <td>0.245</td>\n",
170+
" <td>30</td>\n",
171+
" <td>0</td>\n",
172+
" </tr>\n",
173+
" <tr>\n",
174+
" <th>766</th>\n",
175+
" <td>1</td>\n",
176+
" <td>126</td>\n",
177+
" <td>60</td>\n",
178+
" <td>0</td>\n",
179+
" <td>0</td>\n",
180+
" <td>30.1</td>\n",
181+
" <td>0.349</td>\n",
182+
" <td>47</td>\n",
183+
" <td>1</td>\n",
184+
" </tr>\n",
185+
" <tr>\n",
186+
" <th>767</th>\n",
187+
" <td>1</td>\n",
188+
" <td>93</td>\n",
189+
" <td>70</td>\n",
190+
" <td>31</td>\n",
191+
" <td>0</td>\n",
192+
" <td>30.4</td>\n",
193+
" <td>0.315</td>\n",
194+
" <td>23</td>\n",
195+
" <td>0</td>\n",
196+
" </tr>\n",
197+
" </tbody>\n",
198+
"</table>\n",
199+
"<p>768 rows × 9 columns</p>\n",
200+
"</div>"
201+
],
202+
"text/plain": [
203+
" Pregnancies Glucose BloodPressure SkinThickness Insulin BMI \\\n",
204+
"0 6 148 72 35 0 33.6 \n",
205+
"1 1 85 66 29 0 26.6 \n",
206+
"2 8 183 64 0 0 23.3 \n",
207+
"3 1 89 66 23 94 28.1 \n",
208+
"4 0 137 40 35 168 43.1 \n",
209+
".. ... ... ... ... ... ... \n",
210+
"763 10 101 76 48 180 32.9 \n",
211+
"764 2 122 70 27 0 36.8 \n",
212+
"765 5 121 72 23 112 26.2 \n",
213+
"766 1 126 60 0 0 30.1 \n",
214+
"767 1 93 70 31 0 30.4 \n",
215+
"\n",
216+
" DiabetesPedigreeFunction Age Outcome \n",
217+
"0 0.627 50 1 \n",
218+
"1 0.351 31 0 \n",
219+
"2 0.672 32 1 \n",
220+
"3 0.167 21 0 \n",
221+
"4 2.288 33 1 \n",
222+
".. ... ... ... \n",
223+
"763 0.171 63 0 \n",
224+
"764 0.340 27 0 \n",
225+
"765 0.245 30 0 \n",
226+
"766 0.349 47 1 \n",
227+
"767 0.315 23 0 \n",
228+
"\n",
229+
"[768 rows x 9 columns]"
230+
]
231+
},
232+
"execution_count": 4,
233+
"metadata": {},
234+
"output_type": "execute_result"
235+
}
236+
],
237+
"source": [
238+
"Diabetes"
239+
]
240+
},
241+
{
242+
"cell_type": "code",
243+
"execution_count": 10,
244+
"metadata": {},
245+
"outputs": [],
246+
"source": [
247+
"colnames = list(Diabetes.columns)\n",
248+
"predictors = colnames[:8]\n",
249+
"target = colnames[8]"
250+
]
251+
},
252+
{
253+
"cell_type": "code",
254+
"execution_count": 13,
255+
"metadata": {},
256+
"outputs": [],
257+
"source": [
258+
"# Split dataset\n",
259+
"X_train, X_test, y_train, y_test = train_test_split(Diabetes[predictors],Diabetes[target],test_size=0.3, random_state=0)"
260+
]
261+
},
262+
{
263+
"cell_type": "code",
264+
"execution_count": 14,
265+
"metadata": {},
266+
"outputs": [],
267+
"source": [
268+
"#Import Random Forest Model\n",
269+
"from sklearn.ensemble import RandomForestClassifier\n",
270+
"\n",
271+
"#Create a Gaussian Classifier\n",
272+
"clf=RandomForestClassifier(n_estimators=100)\n",
273+
"\n",
274+
"#Train the model using the training\n",
275+
"clf.fit(X_train,y_train)\n",
276+
"\n",
277+
"y_pred=clf.predict(X_test)"
278+
]
279+
},
280+
{
281+
"cell_type": "code",
282+
"execution_count": 15,
283+
"metadata": {},
284+
"outputs": [
285+
{
286+
"name": "stdout",
287+
"output_type": "stream",
288+
"text": [
289+
"Accuracy: 0.7835497835497836\n"
290+
]
291+
}
292+
],
293+
"source": [
294+
"# Model Accuracy\n",
295+
"print(\"Accuracy:\",metrics.accuracy_score(y_test, y_pred))"
296+
]
297+
}
298+
],
299+
"metadata": {
300+
"kernelspec": {
301+
"display_name": "Python 3",
302+
"language": "python",
303+
"name": "python3"
304+
},
305+
"language_info": {
306+
"codemirror_mode": {
307+
"name": "ipython",
308+
"version": 3
309+
},
310+
"file_extension": ".py",
311+
"mimetype": "text/x-python",
312+
"name": "python",
313+
"nbconvert_exporter": "python",
314+
"pygments_lexer": "ipython3",
315+
"version": "3.6.8"
316+
}
317+
},
318+
"nbformat": 4,
319+
"nbformat_minor": 4
320+
}

0 commit comments

Comments
 (0)