📘 二手车用户数据可视化分析/UsedCar.ipynb

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
from plotly.offline import iplot
import warnings
warnings.filterwarnings('ignore')
df = pd.read_csv("UserCarData.csv")
df.head()

	Sales_ID	name	year	selling_price	km_driven	Region	State or Province	City	fuel	seller_type	transmission	owner	mileage	engine	max_power	torque	seats	sold
0	1	Maruti	2014	450000	145500	East	District of Columbia	Washington	Diesel	Individual	Manual	First_Owner	23.40	1248	74.00	190Nm@ 2000rpm	5	Y
1	2	Skoda	2014	370000	120000	East	New York	New York City	Diesel	Individual	Manual	Second_Owner	21.14	1498	103.52	250Nm@ 1500-2500rpm	5	Y
2	3	Honda	2006	158000	140000	Central	Illinois	Chicago	Petrol	Individual	Manual	Third_Owner	17.70	1497	78.00	12.7@ 2,700(kgm@ rpm)	5	Y
3	4	Hyundai	2010	225000	127000	Central	Illinois	Chicago	Diesel	Individual	Manual	First_Owner	23.00	1396	90.00	22.4 kgm at 1750-2750rpm	5	Y
4	5	Maruti	2007	130000	120000	East	New York	New York City	Petrol	Individual	Manual	First_Owner	16.10	1298	88.20	11.5@ 4,500(kgm@ rpm)	5	Y

# 二手车名称分析
print(f"Most Used Sold Car '{df['name'].value_counts().idxmax()}'")
print(f"Lowest Used Car Sold '{df['name'].value_counts().idxmin()}'")
iplot(px.bar(df['name'].value_counts()[:20],
labels={'value':'Count','name':'Name'},
color=df['name'].value_counts()[:20].index,
text_auto=True,
title='Top Used Cars Sold'
))

Most Used Sold Car 'Maruti'
Lowest Used Car Sold 'Ashok'

# 二手车年份分析
print(f"Most Year Used Sold Car '{df['year'].value_counts().idxmax()}'")
print(f"Lowest Year Used Car Sold '{df['year'].value_counts().idxmin()}'")
iplot(px.bar(df['year'].value_counts()[:20].sort_index(ascending=False),
labels={'value':'Count','year':'Year'},
color_discrete_sequence=['#c72320'],
text_auto=True,
title='Top Year Used Cars Sold'
).update_xaxes(type=('category')))

Most Year Used Sold Car '2017'
Lowest Year Used Car Sold '1995'

# 地区分析
iplot(px.pie(values=df['Region'].value_counts(),
names=['Central','West','East','South'],
title='Region where Sold Used Car'
).update_traces(textinfo='label+percent'))

# 省或州分析
print(f"Top State or Province where Sold Used car '{df['State or Province'].value_counts().idxmax()}'")
print(f"Least State or Province where Sold Used car '{df['State or Province'].value_counts().idxmin()}'")
iplot(px.bar(df['State or Province'].value_counts().sort_values(ascending=True)[:30],
orientation='h',
color=df['State or Province'][:30].index,
title='Top State or Province Sold Used Car',
labels={'value':'Count'}
))

Top State or Province where Sold Used car 'California'
Least State or Province where Sold Used car 'Wyoming'

# 城市分析
print(f"Top City where Sold Used car '{df['City'].value_counts().idxmax()}'")
print(f"Least City where Sold Used car '{df['City'].value_counts().idxmin()}'")
iplot(px.bar(df['City'].value_counts().sort_values(ascending=False)[:20],
color=df['City'][:20].index,
title='Top City Sold Used Car',
labels={'value':'Count'},
text_auto=True
))

Top City where Sold Used car 'New York City'
Least City where Sold Used car 'West Springfield'

# 燃料分析
print(f"Top Fuel Used in Used car '{df['fuel'].value_counts().idxmax()}'")
print(f"Least Fuel Used in Used car '{df['fuel'].value_counts().idxmin()}'")
iplot(px.pie(values=df['fuel'].value_counts(),
names=['Diesel','Petrol','CNG','LPG'],
title='Fuel Used in Used Car'
).update_traces(textinfo='label+percent'))

Top Fuel Used in Used car 'Diesel'
Least Fuel Used in Used car 'LPG'

# 卖家类型分析
print(f"Most Type of Seller '{df['seller_type'].value_counts().idxmax()}'")
iplot(px.pie(values=df['seller_type'].value_counts(),
names=['Individual','Dealer','Trustmark_Dealer'],
title='Types of Seller Used Cars'
).update_traces(textinfo='label+percent'))

Most Type of Seller 'Individual'

# 变速器类型
iplot(px.pie(values=df['transmission'].value_counts(),
names=['Manual','Automatic'],
title='Types of Transmissions Used in Used Sold Cars'
).update_traces(textinfo='label+percent'))

# 业主类型分析
print(f"Most Owner Sold Used Cars '{df['owner'].value_counts().idxmax()}'")
iplot(px.pie(values=df['owner'].value_counts(),
names=['First Owner','Second Owner','Third Owner','Fourth Above Owner','Test Drive Car'],
title='Owners of Used Cars'
).update_traces(textinfo='label+percent'))

Most Owner Sold Used Cars 'First_Owner'

# 转矩分析
iplot(px.bar(df['torque'].value_counts().sort_values(ascending=False)[:20],
orientation='h',
color=df['torque'][:20].index,
title='Top Torque Used in Used Sold Cars',
labels={'value':'Count','torque':'Torque'}
))

# 行驶里程分析
plt.figure(figsize=(15,6))
sns.kdeplot(df['mileage'],fill=True)
plt.xlabel("Mileage")
plt.show()