Linear regression analysis

linear_regression.py

import numpy as np
import pandas as pd
import statsmodels.api as sm
import matplotlib.pyplot as plt
%matplotlib inline


import pandas as pd

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

# Brief look at the data
loansData.head()

# Clean Interest.Rate column
loansData['Interest.Rate'] = loansData['Interest.Rate'].map(lambda x: float(x.rstrip('%')))

# Clean Loan.Length column
loansData['Loan.Length'] = loansData['Loan.Length'].map(lambda x: x.strip(' months'))

# Clean and convert FICO.Range
loansData['FICO.Score'] = loansData['FICO.Range'].map(lambda x: int(x[:3]))

# Review data to make sure cleaning and conversions look correct
loansData.head()

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

a = pd.scatter_matrix(loansData, alpha=0.05, figsize=(10,10), diagonal='hist')

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

# Dependent variable
y = np.matrix(intrate).transpose()

# Independent variables
x1 = np.matrix(fico).transpose()
x2 = np.matrix(loanamt).transpose()

# Put the two indepedent variable columns together to make input matrix
# One column for each indepdent variable
x = np.column_stack([x1,x2])

# Now create linear model
X = sm.add_constant(x)
model = sm.OLS(y, X)
f = model.fit()

f.summary()