prob_lending_club.py

import pandas as pd
import scipy.stats as stats
import matplotlib.pyplot as plt
%matplotlib inline

loansData = pd.read_csv('https://github.com/Thinkful-Ed/curric-data-001-data-sets/raw/master/loans/loansData.csv')

loansData.head()

# Remove rows with null values
loansData.dropna(inplace=True)

# Create Box Plot on Amount.Requested
loansData.boxplot(column='Amount.Requested')
plt.show()

# Create Histogram on Amount.Requested
loansData.hist(column='Amount.Requested')
plt.show()

# Does data look normally distributed? Generate QQ plot to test answer
plt.figure()
graph = stats.probplot(loansData['Amount.Requested'], dist='norm', plot=plt)
plt.show()

# The amounts requested match the amounts funded by investors, which makes logical sense.