linear_regression.py

import pandas as pd
import matplotlib.pyplot as plt
loansData = pd.read_csv(
    'https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv'
)
loansData['Interest.Rate'] = loansData['Interest.Rate'].map(
    lambda x: float(x.rstrip('%'))
)

loansData['Loan.Length'] = loansData['Loan.Length'].map(
    lambda x: float(x.rstrip(' months'))
)

loansData['FICO.Score'] = loansData['FICO.Range'].map(
    lambda x: float(x.split('-')[0])
)

plt.figure()
p = loansData['FICO.Score'].hist()
plt.show()

plt.figure()
a = pd.scatter_matrix(loansData, alpha=0.05, figsize=(16,18))
plt.show()

import numpy as np
import pandas as pd
import statsmodels.api as sm

intrate = loansData['Interest.Rate']
loanamt = loansData['Amount.Requested']
fico = loansData['FICO.Score']

# The dependent variable
y = np.matrix(intrate).transpose()
# The independent variables shaped as columns
x1 = np.matrix(fico).transpose()
x2 = np.matrix(loanamt).transpose()

x = np.column_stack([x1,x2])

X = sm.add_constant(x)
model = sm.OLS(y,X)
f = model.fit()

print f.summary()