GITHUB LINK:https://github.com/rohitkumar20700000/Ex-08-Data-Visualization-
COLAB LINK:https://colab.research.google.com/drive/1fLQbbNdlcIrUR3i6uNCOKmsJuLCLRcph#scrollTo=1zr8hEnE2Xva
To Perform Data Visualization on the given dataset and save the data to a file.
Data visualization is the graphical representation of information and data. By using visual elements like charts, graphs, and maps, data visualization tools provide an accessible way to see and understand trends, outliers, and patterns in data.
Read the given Data
Clean the Data Set using Data Cleaning Process
Apply Feature generation and selection techniques to all the features of the data set
Apply data visualization techniques to identify the patterns of the data.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
df=pd.read_csv("Superstore.csv",encoding='unicode_escape')
df
df.head()
df.info()
df.drop('Row ID',axis=1,inplace=True)
df.drop('Order ID',axis=1,inplace=True)
df.drop('Customer ID',axis=1,inplace=True)
df.drop('Customer Name',axis=1,inplace=True)
df.drop('Country',axis=1,inplace=True)
df.drop('Postal Code',axis=1,inplace=True)
df.drop('Product ID',axis=1,inplace=True)
df.drop('Product Name',axis=1,inplace=True)
df.drop('Order Date',axis=1,inplace=True)
df.drop('Ship Date',axis=1,inplace=True)
print("Updated dataset")
df
df.isnull().sum()
#detecting and removing outliers in current numeric data
plt.figure(figsize=(8,8))
plt.title("Data with outliers")
df.boxplot()
plt.show()
plt.figure(figsize=(8,8))
cols = ['Sales','Quantity','Discount','Profit']
Q1 = df[cols].quantile(0.25)
Q3 = df[cols].quantile(0.75)
IQR = Q3 - Q1
df = df[~((df[cols] < (Q1 - 1.5 * IQR)) |(df[cols] > (Q3 + 1.5 * IQR))).any(axis=1)]
plt.title("Dataset after removing outliers")
df.boxplot()
plt.show()
sns.lineplot(x="Segment",y="Sales",data=df,marker='o')
plt.title("Segment vs Sales")
plt.xticks(rotation = 90)
plt.show()
sns.barplot(x="Segment",y="Sales",data=df)
plt.xticks(rotation = 90)
plt.show()
df.shape
df1 = df[(df.Profit >= 60)]
df1.shape
plt.figure(figsize=(30,8))
states=df1.loc[:,["City","Profit"]]
states=states.groupby(by=["City"]).sum().sort_values(by="Profit")
sns.barplot(x=states.index,y="Profit",data=states)
plt.xticks(rotation = 90)
plt.xlabel=("City")
plt.ylabel=("Profit")
plt.show()
sns.barplot(x="Ship Mode",y="Profit",data=df)
plt.show()
sns.lineplot(x="Ship Mode",y="Profit",data=df)
plt.show()
sns.violinplot(x="Profit",y="Ship Mode",data=df)
sns.pointplot(x=df["Profit"],y=df["Ship Mode"])
states=df.loc[:,["Region","Sales"]]
states=states.groupby(by=["Region"]).sum().sort_values(by="Sales")
sns.barplot(x=states.index,y="Sales",data=states)
plt.xticks(rotation = 90)
plt.xlabel=("Region")
plt.ylabel=("Sales")
plt.show()
df.groupby(['Region']).sum().plot(kind='pie', y='Sales',figsize=(6,9),pctdistance=1.7,labeldistance=1.2)
df["Sales"].corr(df["Profit"])
df_corr = df.copy()
df_corr = df_corr[["Sales","Profit"]]
df_corr.corr()
sns.pairplot(df_corr, kind="scatter")
plt.show()
df4=df.copy()
#encoding
from sklearn.preprocessing import LabelEncoder,OrdinalEncoder,OneHotEncoder
le=LabelEncoder()
ohe=OneHotEncoder
oe=OrdinalEncoder()
df4["Ship Mode"]=oe.fit_transform(df[["Ship Mode"]])
df4["Segment"]=oe.fit_transform(df[["Segment"]])
df4["City"]=le.fit_transform(df[["City"]])
df4["State"]=le.fit_transform(df[["State"]])
df4['Region'] = oe.fit_transform(df[['Region']])
df4["Category"]=oe.fit_transform(df[["Category"]])
df4["Sub-Category"]=le.fit_transform(df[["Sub-Category"]])
#scaling
from sklearn.preprocessing import RobustScaler
sc=RobustScaler()
df5=pd.DataFrame(sc.fit_transform(df4),columns=['Ship Mode', 'Segment', 'City', 'State','Region',
'Category','Sub-Category','Sales','Quantity','Discount','Profit'])
#Heatmap
plt.subplots(figsize=(12,7))
sns.heatmap(df5.corr(),cmap="PuBu",annot=True)
plt.show()
df_corr = df5.copy()
df_corr = df_corr[["Sales","Profit","Segment"]]
df_corr.corr()
df_corr = df5.copy()
df_corr = df_corr[["Sales","Profit","City"]]
df_corr.corr()
df_corr = df5.copy()
df_corr = df_corr[["Sales","Profit","State"]]
df_corr.corr()
df_corr = df5.copy()
df_corr = df_corr[["Sales","Profit","Segment","Ship Mode"]]
df_corr.corr()
df_corr = df5.copy()
df_corr = df_corr[["Sales","Profit","Segment","Ship Mode","Region"]]
df_corr.corr()
Thus, Data Visualization is performed on the given dataset and save the data to a file.