linear_reg1/train linear .py at master · paragDC/linear_reg1 · GitHub

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

# coding: utf-8

# In[1]:


import pandas as pd
import numpy as np


# In[2]:


df = pd.read_csv("C:\\Users\\parag\\Desktop\\train.csv")


# In[3]:


df.head()


# In[6]:


correlation_values = df.select_dtypes(include=[np.number]).corr()
type(correlation_values)


# In[10]:


correlation_values[["Id", "SalePrice"]]


# In[11]:


X = df[["OverallQual", "TotalBsmtSF", "GrLivArea", "GarageArea"]]


# In[12]:


y = df['SalePrice']


# In[15]:


from sklearn.model_selection import train_test_split as tts


# In[16]:


X_train, X_test, y_train, y_test = tts(X, y, test_size= 0.3, random_state= 42)


# In[17]:


from sklearn.linear_model import LinearRegression


# In[19]:


reg = LinearRegression()


# In[20]:


reg.fit(X_train, y_train)


# In[21]:


y_pred = reg.predict(X_test)


# In[24]:


reg.score(X_test, y_test)


# In[25]:


from sklearn.metrics import r2_score


# In[26]:


r2_score(y_test, y_pred)