linear_regression.py

import pandas as pd 
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt 
import scipy.stats as stats
import numpy as np 
import statsmodels.api as sm

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

loansData.dropna(inplace=True)

loansData['Interest.Rate'] = loansData['Interest.Rate'].map(lambda x: float(x.replace('%', '')))
loansData['Loan.Length'] = loansData['Loan.Length'].map(lambda x: float(x.replace(' months', '')))
loansData['FICO.Score'] = loansData['FICO.Range'].map(lambda x: float(x.split('-')[0]))

# plt.figure(1)
# loansData.hist(column='FICO.Score')
# plt.show()

# plt.figure(2)
# stats.probplot(loansData['FICO.Score'], dist='norm', plot=plt)
# plt.show()

#plt.figure(3)
#pd.scatter_matrix(loansData, alpha=.05, figsize=(10,10), diagonal='hist')
#plt.show()

interest_rate = loansData['Interest.Rate']
loan_amount = loansData['Amount.Requested']
fico = loansData['FICO.Score']

y = np.matrix(interest_rate).transpose()
x1 = np.matrix(fico).transpose()
x2 = np.matrix(loan_amount).transpose()

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

X = sm.add_constant(x)
#this appends a column of ones to an array (constant term)

model = sm.OLS(y,X)
result = model.fit()
print(result.summary())