📘 笔记本电脑价格数据可视化分析/LapTOP.ipynb

# 1 Company-字符串-笔记本电脑制造商
# 2 Product-字符串-品牌和型号
# 3 TypeName-字符串-类型（笔记本电脑、超极本、游戏机等）
# 4 Inches-数字-屏幕尺寸
# 5 ScreenResolution-字符串-屏幕分辨率
# 6 Cpu-字符串-中央处理器 (CPU)
# 7 Ram-字符串-笔记本电脑 RAM
# 8 Memory-字符串-硬盘/SSD 内存
# 9 GPU-字符串-图形处理单元 (GPU)
# 10 OpSys-字符串-操作系统
# 11 Weight-字符串-笔记本电脑重量
# 12 Price_euros-数字-价格（欧元）
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import optuna
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
import xgboost as xgb
from xgboost import XGBRegressor
from xgboost import plot_importance
import warnings
warnings.filterwarnings('ignore')
laptop_price = pd.read_csv('laptop_price.csv', encoding='latin-1')
laptop_price.head()
laptop_price.shape
laptop_price.info()
laptop_price.describe()
laptop_price.describe(include='O')
laptop_price.isnull().sum()
laptop_price.duplicated().sum()
df = laptop_price
df = df.drop(['laptop_ID', 'Product'], axis=1)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1303 entries, 0 to 1302
Data columns (total 13 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   laptop_ID         1303 non-null   int64  
 1   Company           1303 non-null   object 
 2   Product           1303 non-null   object 
 3   TypeName          1303 non-null   object 
 4   Inches            1303 non-null   float64
 5   ScreenResolution  1303 non-null   object 
 6   Cpu               1303 non-null   object 
 7   Ram               1303 non-null   object 
 8   Memory            1303 non-null   object 
 9   Gpu               1303 non-null   object 
 10  OpSys             1303 non-null   object 
 11  Weight            1303 non-null   object 
 12  Price_euros       1303 non-null   float64
dtypes: float64(2), int64(1), object(10)
memory usage: 132.5+ KB

# 仅从ScreenResolution列中提取分辨率
df['PPI'] = df['ScreenResolution'].str.extract(r'(\d+x\d+)')
# 创建宽度和高度来计算PPI
df[['Width', 'Height']] = df['PPI'].str.split('x', expand=True).astype('int')
# 计算PPI
df['PPI'] = (((df['Width']**2 + df['Height']**2)**0.5)/df['Inches']).round(2)
# 创建基于术语“触摸屏”的触摸屏专栏
df['Touchscreen'] = df['ScreenResolution'].str.contains('Touchscreen',
case=False, regex=True).astype(int)
# 我们可以删除不需要的列
df = df.drop(['Height', 'Width', 'ScreenResolution'], axis=1)
# 提取Ghz数
df['Cpu_Ghz'] = df['Cpu'].str.extract(r'(\d+(\.\d+)?)GHz')[0].astype(float)
# 提取制造商名称 
df['Cpu_Manufacturer'] = df['Cpu'].str.split(' ').str[0]
df['Cpu_Manufacturer'].value_counts()

Cpu_Manufacturer
Intel      1240
AMD          62
Samsung       1
Name: count, dtype: int64

# 三星的CPU是一个不必要的异常值，所以我们将放弃它。
# 去除异常值并删除Cpu变量
df = df[df['Cpu_Manufacturer'] != 'Samsung']
df = df.drop(['Cpu'], axis=1)
# 从“Ram”列中提取数值
df['Ram'] = df['Ram'].str[:-2].astype(int)
df['Memory'].unique()

array(['128GB SSD', '128GB Flash Storage', '256GB SSD', '512GB SSD',
       '500GB HDD', '256GB Flash Storage', '1TB HDD',
       '32GB Flash Storage', '128GB SSD +  1TB HDD',
       '256GB SSD +  256GB SSD', '64GB Flash Storage',
       '256GB SSD +  1TB HDD', '256GB SSD +  2TB HDD', '32GB SSD',
       '2TB HDD', '64GB SSD', '1.0TB Hybrid', '512GB SSD +  1TB HDD',
       '1TB SSD', '256GB SSD +  500GB HDD', '128GB SSD +  2TB HDD',
       '512GB SSD +  512GB SSD', '16GB SSD', '16GB Flash Storage',
       '512GB SSD +  256GB SSD', '512GB SSD +  2TB HDD',
       '64GB Flash Storage +  1TB HDD', '180GB SSD', '1TB HDD +  1TB HDD',
       '32GB HDD', '1TB SSD +  1TB HDD', '512GB Flash Storage',
       '128GB HDD', '240GB SSD', '8GB SSD', '508GB Hybrid', '1.0TB HDD',
       '512GB SSD +  1.0TB Hybrid', '256GB SSD +  1.0TB Hybrid'],
      dtype=object)

# 这里我们有4种不同类型的内存:SSD, HDD, Flash Storage和Hybrid。我们可以提取存储类型和内存。

df['Memory'] = df['Memory'].str.replace('1TB', '1024GB')
df['Memory'] = df['Memory'].str.replace('1.0TB', '1024GB')
df['Memory'] = df['Memory'].str.replace('2TB', '2048GB')
df['Memory'] = df['Memory'].str.replace('GB', '')
df['Memory'] = df['Memory'].str.replace('  ', '')
df['Storage_1_Type'] = ''
df['Storage_1_Memory'] = 0
df['Storage_2_Type'] = ''
df['Storage_2_Memory'] = 0
storage_types = ['SSD', 'HDD', 'Flash', 'Hybrid']
# Storage_1
for storage_type in storage_types:
    condition = df['Memory'].str.contains(storage_type, case=False, regex=True)
    df.loc[condition & (df['Storage_1_Type'] == ''), 'Storage_1_Type'] = storage_type
    df.loc[condition & (df['Storage_1_Memory'] == 0),'Storage_1_Memory'] = df['Memory'].str.extract(f'(\d+) {storage_type}', expand=False).astype(float)
df['Second_Storage'] = df['Memory'].str.extract(r'(\+\s?\d+\s?\w+)', expand=False).fillna('')
df['Has_Second_Storage'] = df['Second_Storage'].apply(lambda x: False if x == '' else True)
# Storage_2
for storage_type in storage_types:
    condition = df['Second_Storage'].str.contains(storage_type, case=False, regex=True)
    df.loc[condition & (df['Storage_2_Type'] == ''), 'Storage_2_Type'] = storage_type
    df.loc[condition & (df['Storage_2_Memory'] == 0),
    'Storage_2_Memory'] = df['Second_Storage'].str.extract(f'(\d+) {storage_type}', expand=False).astype(float)
# 删除不必要的列
df.drop(['Memory', 'Second_Storage', 'Has_Second_Storage'], axis=1, inplace=True)

# 提取制造商名称
df['Gpu_Manufacturer'] = df['Gpu'].str.split(' ').str[0]
df = df.drop(['Gpu'], axis=1)

# 提取出重量数字
df['Weight'] = df['Weight'].str[:-2].astype(float)
df.head()

	Company	TypeName	Inches	Ram	OpSys	Weight	Price_euros	PPI	Touchscreen	Cpu_Ghz	Cpu_Manufacturer	Storage_1_Type	Storage_1_Memory	Storage_2_Type	Storage_2_Memory	Gpu_Manufacturer
0	Apple	Ultrabook	13.3	8	macOS	1.37	1339.69	226.98	0	2.3	Intel	SSD	128		0	Intel
1	Apple	Ultrabook	13.3	8	macOS	1.34	898.94	127.68	0	1.8	Intel	Flash	128		0	Intel
2	HP	Notebook	15.6	8	No OS	1.86	575.00	141.21	0	2.5	Intel	SSD	256		0	Intel
3	Apple	Ultrabook	15.4	16	macOS	1.83	2537.45	220.53	0	2.7	Intel	SSD	512		0	AMD
4	Apple	Ultrabook	13.3	8	macOS	1.37	1803.60	226.98	0	3.1	Intel	SSD	256		0	Intel

# 按公司划分的产品数量
plt.figure(figsize=(8, 5))
sns.countplot(x='Company', data=df,
order=df['Company'].value_counts().index, palette='crest')
plt.xticks(rotation=45, ha='right')
plt.title('Number of Products by Company', fontsize=10)
plt.xlabel('Company', fontsize=8)
plt.ylabel('Number of Products', fontsize=8)
plt.xticks(fontsize=8)
plt.yticks(fontsize=8)
plt.show()

# 按TypeName, Ram, OpSys划分的产品数量
columns_to_plot = ['TypeName', 'Ram', 'OpSys']
plt.figure(figsize=(10, 4))
for i, feature in enumerate(columns_to_plot):
    plt.subplot(1, 3, i + 1)
    sns.countplot(x=feature, data=df,
    order=df[feature].value_counts().index, palette='crest')
    plt.title(f'Number of Products by {feature}', fontsize=10)
    plt.xlabel(feature, fontsize=8)
    plt.ylabel('Number of Products', fontsize=8)
    if i == 0 or i == 2:
        plt.tick_params(rotation=45, axis='both', labelsize=8)
    else:
        plt.tick_params(axis='both', labelsize=8)
    plt.tight_layout()
plt.show()

# 重量分布
plt.figure(figsize=(8, 3))
sns.histplot(df['Weight'], color='navy', bins=8, alpha=0.6)
plt.title('Distribution of Weight')
plt.xlabel('Weight')
plt.ylabel('Frequency')
plt.show()

# CPU和GPU厂商
features = ['Cpu_Manufacturer', 'Gpu_Manufacturer']
plt.figure(figsize=(8, 3))
for i, feature in enumerate(features, 1):
    plt.subplot(1, 2, i)
    sns.countplot(x=feature, data=df,
    order=df[feature].value_counts().index, palette='crest')
    plt.title(f'Count of Products by {feature}', fontsize=10)
    plt.xlabel('Number of Products', fontsize=8)
    plt.ylabel(feature, fontsize=8)
    plt.xticks(fontsize=8)
    plt.yticks(fontsize=8)
plt.tight_layout()
plt.show()

# 按内存类型划分的产品数量
features = ['Storage_1_Type', 'Storage_2_Type']
plt.figure(figsize=(8, 3))
for i, feature in enumerate(features, 1):
    plt.subplot(1, 2, i)
    sns.countplot(x=feature, data=df,
    order=df[feature].value_counts().index, palette='crest')
    plt.title(f'Count of Products by {feature}', fontsize=10)
    plt.xlabel('Number of Products', fontsize=8)
    plt.ylabel(feature, fontsize=8)
    plt.xticks(fontsize=8)
    plt.yticks(fontsize=8)
plt.tight_layout()
plt.show()

# 存储内存，重量，PPI，英寸和价格的分布
features = ['Storage_1_Memory', 'Storage_2_Memory', 'Weight', 'PPI', 'Inches', 'Price_euros']
plt.figure(figsize=(15, 10))
for i, feature in enumerate(features, 1):
    plt.subplot(2, 3, i)
    sns.histplot(df[feature].dropna(), kde=True, color='navy', bins='auto', alpha=0.6)
    plt.title(f'Histogram of {feature}')
    plt.xlabel(feature)
    plt.ylabel('Frequency')
plt.tight_layout()
plt.show()

# 各公司平均价格
plt.figure(figsize=(12, 6))
order_by_mean_price = df.groupby('Company')['Price_euros'].mean().sort_values(ascending=False).index
sns.barplot(x='Company', y='Price_euros', data=df, palette='crest', order=order_by_mean_price)
plt.title('Mean Price by Company')
plt.xlabel('Company')
plt.ylabel('Mean Price (euros)')
plt.xticks(rotation=45, ha='right')
plt.show()

# 价格与PPI、Ram和Cpu_Ghz的关系
columns_to_plot = ['PPI', 'Ram', 'Cpu_Ghz']
plt.figure(figsize=(8, 3))
for i, feature in enumerate(columns_to_plot):
    plt.subplot(1, 3, i + 1)
    sns.scatterplot(x=feature, data=df, y='Price_euros', color='navy', alpha=0.6)
    plt.title(f'{feature}', fontsize=10)
    plt.xlabel(feature, fontsize=8)
    if i == 0:
        plt.ylabel('Price euros', fontsize=8)
    else: plt.ylabel('')
    plt.tick_params(axis='both', labelsize=8)
plt.tight_layout()
plt.show()

# 箱线图:Cpu_Manufacturer和Gpu_Manufacturer与价格
plt.figure(figsize=(8, 4))
for i, feature in enumerate(['Cpu_Manufacturer', 'Gpu_Manufacturer']):
    plt.subplot(1, 2, i + 1)
    sns.boxplot(x=feature, y='Price_euros', data=df, palette='crest')
    plt.title(f'{feature} vs. Price', fontsize=10)
    plt.xlabel(feature, fontsize=8)
    if i == 0:
        plt.ylabel('Price euros', fontsize=8)
    else: plt.ylabel('')
    plt.tick_params(axis='both', labelsize=8)
plt.tight_layout()
plt.show()

# 相关矩阵
numerical_columns = df.select_dtypes(include=['int', 'float']).columns
corr_matrix = df[numerical_columns].corr()
plt.figure(figsize=(12, 10))
sns.heatmap(corr_matrix, annot=True, cmap='crest', fmt=".2f", linewidths=.5)
plt.title('Correlation Matrix', fontsize=10)
plt.xticks(rotation=45, fontsize=8)
plt.yticks(fontsize=8)
plt.show()

import plotly.express as px
fig = px.sunburst(df, path=['Company','Ram','TypeName'], values='Price_euros',color='Price_euros')
fig.update_layout(margin = dict(t=0, l=0, r=0, b=0))
fig.show()