DEVELOPED BY: HARISH RAGAVENDRA S
REGISTER NO: 212222230045

import pandas as pd
df=pd.read_csv('/Superstore.csv',encoding='windows-1252')
df

df.isnull().sum()

import pandas as pd
import matplotlib.pyplot as plt
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

plt.figure(figsize=(12,10))
plt.title("Data with outliers")
df.boxplot()
plt.show()

cols=['Sales','Quantity','Discount','Profit']
q1=df[cols].quantile(0.75)
q3=df[cols].quantile(0.25)
iqr=q3-q1
low=q1+1.5*iqr
high=q3-1.5*iqr
df2=df[(df[cols]>low)&(df[cols]<high)]
plt.title("Data after removing outlier")
df2.boxplot()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
df2.drop(['Region','State','City','Segment','Ship Mode','Category','Sub-Category'],axis=1,inplace=True)
print("Updated dataset")
df2

#data visualization
#line plots
import seaborn as sns
sns.lineplot(x="Sub-Category",y="Sales",data=df,marker='o')
plt.title("Sub Categories vs Sales")
plt.xticks(rotation = 90)
plt.show()

sns.lineplot(x="Category",y="Profit",data=df,marker='o')
plt.xticks(rotation = 90)
plt.title("Categories vs Profit")
plt.show()

sns.lineplot(x="Region",y="Sales",data=df,marker='o')
plt.xticks(rotation = 90)
plt.title("Region area vs Sales")
plt.show()

sns.lineplot(x="Category",y="Discount",data=df,marker='o')
plt.title("Categories vs Discount")
plt.show()

sns.lineplot(x="Sub-Category",y="Quantity",data=df,marker='o')
plt.xticks(rotation = 90)
plt.title("Sub Categories vs Quantity")
plt.show()

#count plot
plt.figure(figsize=(10,7))
sns.countplot(x ='Segment', data = df,hue = 'Sub-Category')
sns.countplot(x ='Region', data = df,hue = 'Segment')
sns.countplot(x ='Category', data = df,hue='Discount')
sns.countplot(x ='Ship Mode', data = df,hue = 'Quantity')

#Histogram
sns.histplot(data = df,x = 'Region',hue='Ship Mode')
sns.histplot(data = df,x = 'Category',hue='Quantity')
sns.histplot(data = df,x = 'Sub-Category',hue='Category')
plt.xticks(rotation = 90)
plt.show()
sns.histplot(data = df,x = 'Quantity',hue='Segment')
plt.hist(data = df,x = 'Profit')
plt.show()

#bar plots
sns.barplot(x="Sub-Category",y="Sales",data=df)
plt.title("Sub Categories vs Sales")
plt.xticks(rotation = 90)
plt.show()

sns.barplot(x="Category",y="Profit",data=df)
plt.title("Categories vs Profit")
plt.show()

sns.barplot(x="Sub-Category",y="Quantity",data=df)
plt.title("Sub Categories vs Quantity")
plt.xticks(rotation = 90)
plt.show()

sns.barplot(x="Category",y="Discount",data=df)
plt.title("Categories vs Discount")
plt.show()

plt.figure(figsize=(12,7))
sns.barplot(x="State",y="Sales",data=df)
plt.title("States vs Sales")
plt.xticks(rotation = 90)
plt.show()

plt.figure(figsize=(25,8))
sns.barplot(x="State",y="Sales",hue="Region",data=df)
plt.title("State vs Sales based on Region")
plt.xticks(rotation = 90)
plt.show()

#KDE plot
sns.kdeplot(x="Profit", data = df,hue='Category')
sns.kdeplot(x="Sales", data = df,hue='Region')
sns.kdeplot(x="Quantity", data = df,hue='Segment')
sns.kdeplot(x="Discount", data = df,hue='Segment')

#violin plot
sns.violinplot(x="Profit",data=df)
sns.violinplot(x="Discount",y="Ship Mode",data=df)
sns.violinplot(x="Quantity",y="Ship Mode",data=df)