chi_squared.py

from scipy import stats
import collections

# Apply collections.Counter() on # open credit lines in Loans data to get counts of observations for each # credit lines

# Load reduced version of Lending Club dataset
loansData = pd.read_csv("https://github.com/Thinkful-Ed/curric-data-001-data-sets/raw/master/loans/loansData.csv")

# Drop null rows
loansData.dropna(inplace=True)

freq = collections.Counter(loansData['Open.CREDIT.Lines'])

plt.figure()
plt.bar(freq.keys(), freq.values(), width=1)
plt.show()

print len(freq)

# Chi-squared test (scipy.stats.chisquare) to verify answer
chi, p = stats.chisquare(freq.values())

print chi
print p