-
Notifications
You must be signed in to change notification settings - Fork 15
/
Logistic Regression.py
67 lines (48 loc) · 2.17 KB
/
Logistic Regression.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
# -*- coding: utf-8 -*-
"""
Created on Wed Nov 11 13:55:19 2020
@author: user
"""
import pandas as pd
import numpy as np
from sklearn import preprocessing
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.model_selection import train_test_split
###############################################################################
datainput = pd.read_csv("datafile.csv", delimiter = ',')
#preprocessing
Profit = (datainput.iloc[:,5]*datainput.iloc[:,6]-(datainput.iloc[:,2]+datainput.iloc[:,3]+(datainput.iloc[:,5]*datainput.iloc[:,4]))).values
Profit = Profit.reshape(49,1)
Profitcopy = (datainput.iloc[:,5]*datainput.iloc[:,6]-(datainput.iloc[:,2]+datainput.iloc[:,3]+(datainput.iloc[:,5]*datainput.iloc[:,4]))).values
for i in range (0,49):
if Profit[i][0]>0:
Profit[i][0] = 1
else:
Profit[i][0] = 0
X = datainput[['Crop', 'State', 'Cost of Cultivation (`/Hectare) A2+FL',
'Cost of Cultivation (`/Hectare) C2','Cost of Production (`/Quintal) C2', 'Support price']].values
#label encoder to categorical data
labelencoder_X = preprocessing.LabelEncoder()
X[:,0] = labelencoder_X.fit_transform(X[:, 0])
X[:,1] = labelencoder_X.fit_transform(X[:, 1])
#One hot encoder
columnTransformer = ColumnTransformer([('encoder', OneHotEncoder(),[0])], remainder='passthrough')
x2 = np.array(columnTransformer.fit_transform(X), dtype = np.float)
columnTransformer = ColumnTransformer([('encoder', OneHotEncoder(),[10])], remainder='passthrough')
x3 = np.array(columnTransformer.fit_transform(x2), dtype = np.float)
#output col in y
y = Profit
#Splitting
X_train, X_test, y_train, y_test = train_test_split(x3, y, test_size=0.3, random_state=3)
#Logitic
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
matrixForLR = confusion_matrix(y_test, y_pred)
matrix = confusion_matrix(y_test, y_pred)
from sklearn.metrics import classification_report
result = classification_report(y_test,y_pred,labels=[1,0])
print('Classification report : \n',result)