-
Notifications
You must be signed in to change notification settings - Fork 0
/
LinearRegression.py
127 lines (81 loc) · 3.06 KB
/
LinearRegression.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
import warnings
warnings.filterwarnings('ignore')
import os
import boto3
import io
import sagemaker
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
%matplotlib inline
import sklearn
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LinearRegression
import pickle,gzip,urllib,json,csv
from sklearn import preprocessing
from sagemaker import get_execution_role
role = get_execution_role()
s3 = boto3.resource('s3')
bucket_name = 'aws-machinelearning-chez'
object_key = 'weatherhistory2.csv'
s3_client = boto3.client('s3')
response = s3_client.get_object(Bucket=bucket_name, Key=object_key)
response_body = response["Body"].read()
weather = pd.read_csv(io.BytesIO(response_body), header=0, delimiter=",", low_memory=False)
weather.head()
weather.columns
weather.shape
weather.describe()
weather.info()
weather.isnull().any()
weather.isnull().all()
round(100*(weather.isnull().sum()/len(weather.index)),2)
weather['Precip Type'].value_counts()
weather.loc[weather['Precip Type'].isnull(),'Precip Type']='rain'
round(100*(weather.isnull().sum()/len(weather.index)),2)
#Input binary values in type column
weather.loc[weather['Precip Type']=='rain','Precip Type']=1
weather.loc[weather['Precip Type']=='snow','Precip Type']=0
weather_num=weather[list(weather.dtypes[weather.dtypes!='odject'].index)]
weather_y = weather_num.pop('Temperature (C)')
weather_x = weather_num
train_x,test_x,train_y,test_y = train_test_split(weather_x,weather_y,test_size = 0.2,random_state=4)
train_x.head()
test_x.head()
to_drop = ['Formatted Date','Summary','Daily Summary']
weather.drop(to_drop, inplace=True, axis=1)
train_x.drop(to_drop, inplace=True, axis=1)
test_x.drop(to_drop, inplace=True, axis=1)
train_x.head()
test_x.head()
train_x.head()
model = LinearRegression()
model.fit(train_x,train_y)
prediction = model.predict(test_x)
## Calculating the error
np.mean((prediction-test_y)**2)
pd.DataFrame({'actual':test_y,
'prediction':prediction,
'diff':(test_y-prediction)})
#**************************************************************************************************
##Using Decision Tree Regressor
from sklearn.tree import DecisionTreeRegressor
regressor = DecisionTreeRegressor(random_state=0)
regressor.fit(train_x,train_y)
prediction3 = regressor.predict(test_x)
np.mean((prediction3-test_y)**2)
pd.DataFrame({'actual':test_y,
'prediction':prediction3,
'diff':(test_y-prediction3)})
#**************************************************************************************************
## Using Random Forest
from sklearn.ensemble import RandomForestRegressor
regr = RandomForestRegressor(max_depth=10,random_state=0,n_estimators=100)
regr.fit(train_x,train_y)
prediction4 = regr.predict(test_x)
np.mean((prediction4-test_y)**2)
pd.DataFrame({'actual':test_y,
'prediction':prediction4,
'diff':(test_y-prediction4)})
#**************************************************************************************************