correlation.py

#Import statements to get required modules
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

#Loading the dataset into a dataframe
df=pd.read_csv('./Housing_Dataset.csv',encoding ='latin1')
dic={'House_Type_Confidence':df['house_types:confidence'],'Side_Walk_Confidence':df['sidewalk_ok:confidence']}
test_frame=pd.DataFrame(dic)

#Plotting the results
sns.set_context("talk")
sns.lmplot(x='House_Type_Confidence', y='Side_Walk_Confidence',data=test_frame,size=4, aspect=3)
plt.title('Scatter plot of House_Type & Side_Walk Confidence')
plt.xlabel('House_Type_Confidence')
plt.ylabel('Side_Walk_Confidence')
test_frame.corr(method='pearson', min_periods=1)