-
Notifications
You must be signed in to change notification settings - Fork 1
/
modeldoneinpy.py
238 lines (169 loc) · 7.48 KB
/
modeldoneinpy.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
# -*- coding: utf-8 -*-
"""train.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1tXCMlLyiCLHQ-5oRiihWAffyVTBUEuVl
"""
# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory
import os
!pip install seaborn
# Commented out IPython magic to ensure Python compatibility.
import seaborn as sns
import math
import matplotlib.pyplot as plt
# %matplotlib inline
train_data=pd.read_csv('https://raw.githubusercontent.com/nimishbongale/devengers-hackathon/master/trainms.csv?token=AKLHGWLWGVVVQGQRKTZATRK5ONMUM')
test_data=pd.read_csv('https://raw.githubusercontent.com/nimishbongale/devengers-hackathon/master/testms.csv?token=AKLHGWNGNCHEF4H5ZPQWUWC5ONM5Q')
train_data
test_data
train_data=pd.concat([train_data,test_data])
train_data
train_data.columns
train_data.drop(['s.no', 'Timestamp', 'leave', 'coworkers', 'benefits', 'care_options', 'anonymity', ],axis=1,inplace=True)
train_data.info()
train_data.isnull()
train_data["self_employed"].fillna("No",inplace=True)
train_data.isnull()
sns.heatmap(train_data.isnull(),yticklabels=False,cmap="viridis")
def rem(train_data,field):
remwork=pd.get_dummies(train_data[field],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop([field],axis=1,inplace=True)
train_data.head()
state=pd.get_dummies(train_data["state"],drop_first=True)
state.head()
workinter=pd.get_dummies(train_data["work_interfere"],drop_first=True)
workinter.head()
train_data = pd.concat([train_data,state,workinter],axis=1)
train_data.head()
train_data.drop(['state','work_interfere'],axis=1,inplace=True)
train_data.head()
sns.heatmap(train_data.isnull(),yticklabels=False,cmap="viridis")
sns.heatmap(train_data.isnull(),yticklabels=False,cbar=False)
print(sum(train_data.isnull().sum()))
train_data.loc[:, train_data.isna().any()]
train_data.drop(['comments'],axis=1,inplace=True)
train_data.head()
train_data.isnull().sum()
def convert(str):
if str=='m' or str=='Male' or str=='male' or str=='Male ' or str=='Mal' or str=='Mail' or str=='Make' or str=='Guy (-ish) ^_^' or str=='maile' or str=='something kinda male?':
return 'M'
elif str=='f' or str=='Female' or str=='female' or str=='Femake' or str=='Female ' or str=='Woman' or str=='woman':
return 'F'
else:
return str
train_data["Gender"]=train_data["Gender"].apply(convert)
Gender=pd.get_dummies(train_data["Gender"],drop_first=True)
print(Gender.columns)
train_data = pd.concat([train_data,Gender],axis=1)
train_data.drop(['Gender'],axis=1,inplace=True)
train_data.head()
country=pd.get_dummies(train_data["Country"],drop_first=True)
country.head()
train_data = pd.concat([train_data,country],axis=1)
train_data.drop(['Country'],axis=1,inplace=True)
train_data.head()
se=pd.get_dummies(train_data["self_employed"],drop_first=True)
se.head()
train_data = pd.concat([train_data,se],axis=1)
train_data.drop(['self_employed'],axis=1,inplace=True)
train_data.head()
famhis=pd.get_dummies(train_data["family_history"],drop_first=True)
famhis.head()
train_data = pd.concat([train_data,famhis],axis=1)
train_data.drop(['family_history'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["remote_work"],drop_first=True)
remwork.head()
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['remote_work'],axis=1,inplace=True)
train_data.head()
print(train_data.columns)
remwork=pd.get_dummies(train_data["tech_company"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['tech_company'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["no_employees"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['no_employees'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["wellness_program"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['wellness_program'],axis=1,inplace=True)
train_data.head()
train_data.head()
remwork=pd.get_dummies(train_data["seek_help"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['seek_help'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["mental_health_consequence"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['mental_health_consequence'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["phys_health_consequence"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['phys_health_consequence'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["supervisor"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['supervisor'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["mental_health_interview"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['mental_health_interview'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["phys_health_interview"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['phys_health_interview'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["mental_vs_physical"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['mental_vs_physical'],axis=1,inplace=True)
train_data.head()
remwork=pd.get_dummies(train_data["obs_consequence"],drop_first=True)
train_data = pd.concat([train_data,remwork],axis=1)
train_data.drop(['obs_consequence'],axis=1,inplace=True)
train_data.head()
train_data["treatment"]=train_data["treatment"].apply(lambda x: 1 if x=='Yes' else 0 if x=='No' else -1)
train_data
test_data
test_data=train_data.iloc[1000:]
train_data=train_data.iloc[:1000]
train_data.columns
test_data.columns
Y=train_data["treatment"]
X=train_data.drop(['treatment'], axis=1)
from sklearn.model_selection import train_test_split
X_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=0.2,random_state=0)
from sklearn.metrics import mean_squared_error
from sklearn.ensemble import RandomForestClassifier
regressor=RandomForestClassifier(n_estimators=1000,criterion = 'entropy',random_state=0)
regressor.fit(X_train,Y_train)
Y_pred=regressor.predict(X_test)
mean_squared_error(Y_test,Y_pred)
from sklearn.ensemble import ExtraTreesClassifier
regressor=ExtraTreesClassifier(n_estimators=1000,max_features= 100,criterion= 'entropy',min_samples_split= 2,max_depth= 50, min_samples_leaf= 5)
regressor.fit(X_train,Y_train)
Y_pred=regressor.predict(X_test)
mean_squared_error(Y_test,Y_pred)
from sklearn.metrics import accuracy_score
accuracy_score(Y_test,Y_pred)
test_data=test_data.drop(['treatment'], axis=1)
Y_final_pred=regressor.predict(test_data)
for item in Y_final_pred:
print("Yes" if item==1 else "No")
import csv
row = ["Yes" if i==1 else "No" for i in Y_final_pred]
with open('result.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(row)
csvFile.close()
!ls
from google.colab import files
files.download('result.csv')