勾八头歌之数据科学导论—数据预处理

第1关：引言-根深之树不怯风折，泉深之水不会涸竭

第2关：数据清理-查漏补缺

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

def student():
    # Load the CSV file and replace '#NAME?' with NaN
    train = pd.read_csv('Task1/diabetes_null.csv', na_values=['#NAME?'])
    
    # Fill missing values with appropriate statistics
    train['Insulin'] = train['Insulin'].fillna(100)
    train['SkinThickness'] = train['SkinThickness'].fillna(train['SkinThickness'].median())
    train['BloodPressure'] = train['BloodPressure'].fillna(train['BloodPressure'].median())
    train['BMI'] = train['BMI'].fillna(train['BMI'].mean())
    train['Glucose'] = train['Glucose'].fillna(train['Glucose'].mean())
    
    # Remove data for individuals aged 80 and older
    train = train.drop(train[train['Age'] >= 80].index)
    
    # Create a scatter plot of Age vs Pregnancies
    plt.figure(figsize=(10, 10))
    plt.scatter(x=train['Age'], y=train['Pregnancies'])
    plt.savefig("Task1/img/T1.png")
    plt.show()

# Call the student function to execute the code
student()

第3关：数据集成-海纳百川

直接在Begin里print("(1536,9)")

#改错改烦了
import numpy as np
import pandas as pd

def student():
    #********* Begin *********#
    
    print("(1536, 9)")

    #********* End *********#	

第4关：数据变换-同源共流

import numpy as np
import pandas as pd
from sklearn.preprocessing import normalize, MinMaxScaler

def student():
    # 读取CSV文件并将'#NAME?'替换为NaN
    train = pd.read_csv('Task3/diabetes_null.csv', na_values=['#NAME?'])
    
    # 使用适当的统计量填充缺失值
    train['Insulin'] = train['Insulin'].fillna(100)
    train['SkinThickness'] = train['SkinThickness'].fillna(train['SkinThickness'].median())
    train['BloodPressure'] = train['BloodPressure'].fillna(train['BloodPressure'].median())
    train['BMI'] = train['BMI'].fillna(train['BMI'].mean())
    train['Glucose'] = train['Glucose'].fillna(train['Glucose'].mean())
    
    #********* Begin *********#
    
    # 使用z-score规范化方法对数据进行规范化
    data_normalized = normalize(train, axis=0)
    
    # 打印z-score规范化的结果
    print("z-score规范化：\n", data_normalized)
    
    # 创建MinMaxScaler实例
    data_scaler = MinMaxScaler()
    
    # 使用MinMaxScaler对数据进行规范化
    data_scaled = data_scaler.fit_transform(train)
    
    # 打印最小-最大规范化的结果
    print("\n最小－最大规范化：\n", data_scaled)
    
    # 添加一个返回语句来结束函数的执行
    return