Thinkful Unit 2 Lesson 2.3

chi_squared.py

from scipy import stats
# import matplotlib.pyplot as plt
import pandas as pd
import collections

loansData = pd.read_csv(
    'https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv'
)
loansData.dropna(inplace=True)
freq = collections.Counter(loansData['Open.CREDIT.Lines'])
# plt.figure()
# plt.bar(freq.keys(), freq.values(), width=1)
# plt.show()
chi, p = stats.chisquare(freq.values())

print p, chi