import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
sns.set_style("whitegrid")
from scipy.stats import f_oneway
import warnings
warnings.filterwarnings('ignore')
df = pd.read_csv("smartphones.csv")
df.head()
df.shape
df.info()
df.describe()
df.describe(include='O')
df.isnull().sum()
df.duplicated().sum()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 980 entries, 0 to 979
Data columns (total 22 columns):
 #   Column                     Non-Null Count  Dtype  
---  ------                     --------------  -----  
 0   brand_name                 980 non-null    object 
 1   model                      980 non-null    object 
 2   price                      980 non-null    int64  
 3   avg_rating                 879 non-null    float64
 4   5G_or_not                  980 non-null    int64  
 5   processor_brand            960 non-null    object 
 6   num_cores                  974 non-null    float64
 7   processor_speed            938 non-null    float64
 8   battery_capacity           969 non-null    float64
 9   fast_charging_available    980 non-null    int64  
 10  fast_charging              769 non-null    float64
 11  ram_capacity               980 non-null    int64  
 12  internal_memory            980 non-null    int64  
 13  screen_size                980 non-null    float64
 14  refresh_rate               980 non-null    int64  
 15  num_rear_cameras           980 non-null    int64  
 16  os                         966 non-null    object 
 17  primary_camera_rear        980 non-null    float64
 18  primary_camera_front       975 non-null    float64
 19  extended_memory_available  980 non-null    int64  
 20  resolution_height          980 non-null    int64  
 21  resolution_width           980 non-null    int64  
dtypes: float64(8), int64(10), object(4)
memory usage: 168.6+ KB

0

import pandas as pd
# 读取 CSV 文件
df = pd.read_csv('smartphones.csv')
# 修改列名
df = df.rename(columns={
    'brand_name': 'Brand', 
    'model': 'Model', 
    'price': 'Final Price', 
    'ram_capacity': 'RAM', 
    'internal_memory': 'Storage', 
    'avg_rating': 'Color', 
    '5G_or_not': 'Free', 
    'processor_brand': 'Smartphone'
})
# 保存修改后的 CSV 文件
df.to_csv('smartphonesnew_file.csv', index=False)

df = df.rename(columns={'model': 'Model'})
df = df.rename(columns={'brand_name': 'Brand'})
df = df.rename(columns={'model': 'Model'})
df = df.rename(columns={'model': 'Model'})
df = df.rename(columns={'model': 'Model'})

	price	avg_rating	5G_or_not	num_cores	processor_speed	battery_capacity	fast_charging_available	fast_charging	ram_capacity	internal_memory	screen_size	refresh_rate	num_rear_cameras	primary_camera_rear	primary_camera_front	extended_memory_available	resolution_height	resolution_width
count	980.000000	879.000000	980.000000	974.000000	938.000000	969.000000	980.000000	769.000000	980.000000	980.000000	980.000000	980.000000	980.000000	980.000000	975.000000	980.000000	980.000000	980.000000
mean	32520.504082	7.825825	0.560204	7.772074	2.427217	4817.748194	0.854082	46.126138	6.560204	141.036735	6.536765	92.256122	2.814286	50.319286	16.589744	0.630612	2214.663265	1075.852041
std	39531.812669	0.740285	0.496616	0.836845	0.464090	1009.540054	0.353205	34.277870	2.744378	107.134516	0.349162	28.988052	0.776441	33.000968	10.876944	0.482885	516.484254	290.164931
min	3499.000000	6.000000	0.000000	4.000000	1.200000	1821.000000	0.000000	10.000000	1.000000	8.000000	3.540000	60.000000	1.000000	2.000000	0.000000	0.000000	480.000000	480.000000
25%	12999.000000	7.400000	0.000000	8.000000	2.050000	4500.000000	1.000000	18.000000	4.000000	64.000000	6.500000	60.000000	2.000000	24.000000	8.000000	0.000000	1612.000000	1080.000000
50%	19994.500000	8.000000	1.000000	8.000000	2.300000	5000.000000	1.000000	33.000000	6.000000	128.000000	6.580000	90.000000	3.000000	50.000000	16.000000	1.000000	2400.000000	1080.000000
75%	35491.500000	8.400000	1.000000	8.000000	2.840000	5000.000000	1.000000	66.000000	8.000000	128.000000	6.670000	120.000000	3.000000	64.000000	16.000000	1.000000	2408.000000	1080.000000
max	650000.000000	8.900000	1.000000	8.000000	3.220000	22000.000000	1.000000	240.000000	18.000000	1024.000000	8.030000	240.000000	4.000000	200.000000	60.000000	1.000000	3840.000000	2460.000000

📘 智能手机价格数据集可视化分析/01.ipynb