emredjan

Keybase proof

I hereby claim:

• I am emredjan on github.
• I am emredjan (https://keybase.io/emredjan) on keybase.
• I have a public key ASAXSNkoaMfSyBS4L6szj2-YhodeBmD8sangtMLbuYXgzwo

To claim this, I am signing this object:

emredjan

model = lm(mpg ~ . - name, data=Auto)

par(mfrow=c(2,2)) # Plot 4 plots in same screen
plot(model)

emredjan

%matplotlib inline

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import statsmodels.formula.api as smf

from statsmodels.graphics.gofplots import ProbPlot

emredjan

auto = pd.read_csv('Auto.csv', na_values=['?'])
auto.dropna(inplace=True)
auto.reset_index(drop=True, inplace=True)

emredjan

model_f = 'mpg ~ cylinders + \
                 displacement + \
                 horsepower + \
                 weight + \
                 acceleration + \
                 year + \
                 origin'

model = smf.ols(formula=model_f, data=auto)
model_fit = model.fit()

emredjan

# fitted values (need a constant term for intercept)
model_fitted_y = model_fit.fittedvalues

# model residuals
model_residuals = model_fit.resid

# normalized residuals
model_norm_residuals = model_fit.get_influence().resid_studentized_internal

# absolute squared normalized residuals

emredjan

plot_lm_1 = plt.figure(1)
plot_lm_1.set_figheight(8)
plot_lm_1.set_figwidth(12)

plot_lm_1.axes[0] = sns.residplot(model_fitted_y, 'mpg', data=auto, 
                          lowess=True, 
                          scatter_kws={'alpha': 0.5}, 
                          line_kws={'color': 'red', 'lw': 1, 'alpha': 0.8})

plot_lm_1.axes[0].set_title('Residuals vs Fitted')

emredjan

QQ = ProbPlot(model_norm_residuals)
plot_lm_2 = QQ.qqplot(line='45', alpha=0.5, color='#4C72B0', lw=1)

plot_lm_2.set_figheight(8)
plot_lm_2.set_figwidth(12)

plot_lm_2.axes[0].set_title('Normal Q-Q')
plot_lm_2.axes[0].set_xlabel('Theoretical Quantiles')
plot_lm_2.axes[0].set_ylabel('Standardized Residuals');

emredjan

plot_lm_3 = plt.figure(3)
plot_lm_3.set_figheight(8)
plot_lm_3.set_figwidth(12)

plt.scatter(model_fitted_y, model_norm_residuals_abs_sqrt, alpha=0.5)
sns.regplot(model_fitted_y, model_norm_residuals_abs_sqrt, 
            scatter=False, 
            ci=False, 
            lowess=True,
            line_kws={'color': 'red', 'lw': 1, 'alpha': 0.8})

emredjan

plot_lm_4 = plt.figure(4)
plot_lm_4.set_figheight(8)
plot_lm_4.set_figwidth(12)

plt.scatter(model_leverage, model_norm_residuals, alpha=0.5)
sns.regplot(model_leverage, model_norm_residuals, 
            scatter=False, 
            ci=False, 
            lowess=True,
            line_kws={'color': 'red', 'lw': 1, 'alpha': 0.8})