Exploratory Data Analysis With Chi Square Contingency

Download Note Book Here

This Exploratory Data Analysis is my own personal learning practice in this practice i did analysis from datasets i downloaded from kaggle.com

Plotly For Visualization

Seaborn For Visualization

Import Necessary Libraries

# Libraries for data manipulation
import pandas as pd
import numpy as np

# Libraries for visualization
import seaborn as sns
import matplotlib.pyplot as plt

# Libraries for operatingsystem
import warnings
import os
warnings.filterwarnings('ignore')

Importing Datasets

# Reading the dataset 
df = pd.read_csv(r'C:\Users\user\dl-course-data\abalone.csv')

df.head()

Checking data information

# Shape of dataset
df.shape

# Checking the null value in the dataset
df.isnull().sum()

# Infromation about dataset
df.info()

# Statistical description of dataset
df.describe().T

# Extracting a unique values of type column
a = df['Type'].unique()

print(a)

# Finding thee counts of Type
b = df['Type'].value_counts()

print(b)

# Computing Rings by Type

df.groupby(["Type"])["Rings"].count().reset_index(name="count")

Adding ID Column to dataset

df['id'] = range(1, len(df)+1)

df.head()

Correlation

# finding the correlation of datasets
correlation = df.corr()

# Longest Shell has the highest positive correlation value

fig = px.imshow(correlation,text_auto=True,aspect="auto")
fig.show()

# Type M has the highest number of percentage

import plotly.express as px
import pandas as pd 

fig = px.pie(df, values='id', names='Type', title='Abalone Type By Height')
fig.update_traces(hoverinfo='label+percent', textinfo='label+percent', textfont_size=20, pull=[0.1,0.1,0.1],
                  marker=dict(colors=colors, line=dict(color='#000000', width=2)))
fig.show()

#Type M has the highest number of counts

import plotly.express as px

fig = px.bar(df, x='Type', y='id', color='id')
fig.show()

# Include nbins= number_of_bins to specify histogram shape

px.histogram(df, x="id", color="Type")

# Cross tb for Type and Rings for easy understanding

cross_tab = pd.crosstab(df["Type"],df["Rings"],margins=True)

cross_tab

# The F type is the factor determinant for the whole parameters

sns.factorplot(df["Type"],df["Rings"],data=df)

import numpy as np
import pandas as pd
from scipy.stats import chi2_contingency


alpha = 0.05

stats,p_value,degrees_of_freedom,expected = chi2_contingency(cross_tab)

if p_value > alpha:
    print(f'Accept Null Hypothesis\n p_value is {p_value}\n Ringss are independent of Types')
else:
    print(f'Reject Null Hypothesis\n p_value is {p_value}\n Rings are not independent of Types')

References