mtcars Data Analysis

import pandas as pd
import numpy as np
import scipy.stats as stats
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()

#Models
from sklearn.linear_model import LinearRegression

filename = "https://gist.githubusercontent.com/seankross/a412dfbd88b3db70b74b/raw/5f23f993cd87c283ce766e7ac6b329ee7cc2e1d1/mtcars.csv"
mtcars_data = pd.read_csv(filename)

mtcars_data.head()

	model	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.0	6	160.0	110	3.90	2.620	16.46	0	1	4	4
1	Mazda RX4 Wag	21.0	6	160.0	110	3.90	2.875	17.02	0	1	4	4
2	Datsun 710	22.8	4	108.0	93	3.85	2.320	18.61	1	1	4	1
3	Hornet 4 Drive	21.4	6	258.0	110	3.08	3.215	19.44	1	0	3	1
4	Hornet Sportabout	18.7	8	360.0	175	3.15	3.440	17.02	0	0	3	2

EDA

fig, ax = plt.subplots(figsize = (10, 6), ncols = 2)
sns.boxplot(x = mtcars_data.cyl, y = mtcars_data.disp, ax=ax[0])
sns.boxplot(x = mtcars_data.cyl, y = mtcars_data.wt, ax=ax[1])
plt.show()

fig2, ax2 = plt.subplots(ncols=2, figsize = (12,6))
sns.scatterplot(x= mtcars_data.wt, y=mtcars_data.mpg, ax = ax2[0])
ax2[0].set_title("Original Data")
sns.scatterplot(x= np.log(mtcars_data.wt), y=np.log(mtcars_data.mpg), ax = ax2[1])
ax2[1].set_title("Log-transformed Data")
plt.show()

Regression analysis on original data and log-transformed data for MPG and WT

normal_model = LinearRegression()
normal_model.fit(mtcars_data.wt.values.reshape(-1,1), mtcars_data.mpg)
log_model = LinearRegression()
log_model.fit(np.log(mtcars_data.wt.values.reshape(-1,1)), np.log(mtcars_data.mpg))

LinearRegression()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

fig2, ax2 = plt.subplots(ncols=2, figsize = (12,6))
sns.scatterplot(x= mtcars_data.wt, y=mtcars_data.mpg, ax = ax2[0])
ax2[0].plot(mtcars_data.wt,normal_model.predict(mtcars_data.wt.values.reshape(-1,1)))
sns.scatterplot(x= np.log(mtcars_data.wt), y=np.log(mtcars_data.mpg), ax = ax2[1])
ax2[1].plot(np.log(mtcars_data.wt.values), log_model.predict(np.log(mtcars_data.wt.values.reshape(-1,1))))
ax2[0].set_title("Original Data")
ax2[1].set_title("Log-transformed Data")
plt.show()

Contingency Table : CYL and AM, Chi-square Independent Test

table = pd.crosstab(index = mtcars_data.am, columns = mtcars_data.cyl, values = mtcars_data.cyl, aggfunc="count")
table

cyl	4	6	8
am
0	3	4	12
1	8	3	2

stats.chi2_contingency(table)

Chi2ContingencyResult(statistic=8.740732951259268, pvalue=0.012646605046107276, dof=2, expected_freq=array([[6.53125, 4.15625, 8.3125 ],
       [4.46875, 2.84375, 5.6875 ]]))