import pandas as pd
import numpy as np
from scipy.stats import shapiro

# 創(chuàng)建示例數(shù)據(jù)
data = np.random.normal(loc=0, scale=1, size=1000)
series = pd.Series(data)

# Shapiro-Wilk檢驗(yàn)
statistic, p_value = shapiro(series)

# 解釋檢驗(yàn)結(jié)果
if p_value > 0.05:
    print("數(shù)據(jù)可能符合正態(tài)分布")
else:
    print("數(shù)據(jù)不符合正態(tài)分布")

import pandas as pd

# 創(chuàng)建示例數(shù)據(jù)
data = {
    'A': [1, 2, 3, 4, 5],
    'B': [5, 4, 3, 2, 1],
    'C': [1, 1, 2, 2, 3]
}
df = pd.DataFrame(data)

# 計(jì)算相關(guān)系數(shù)
correlation_matrix = df.corr()

print("相關(guān)系數(shù)矩陣:")
print(correlation_matrix)

相關(guān)性和正態(tài)性綜合性示例：
import pandas as pd
import numpy as np
from scipy.stats import shapiro
from scipy.stats import pearsonr

# 創(chuàng)建示例數(shù)據(jù)集
data = {
    'A': np.random.normal(loc=0, scale=1, size=1000),
    'B': np.random.normal(loc=0, scale=1, size=1000),
    'C': np.random.normal(loc=0, scale=1, size=1000)
}
df = pd.DataFrame(data)

# 正態(tài)性分析
for column in df.columns:
    series = df[column]
    statistic, p_value = shapiro(series)
    if p_value > 0.05:
        print(f"列 '{column}' 可能符合正態(tài)分布 (p-value={p_value:.4f})")
    else:
        print(f"列 '{column}' 不符合正態(tài)分布 (p-value={p_value:.4f})")

# 相關(guān)性分析
correlation_matrix = df.corr()

print("\n相關(guān)系數(shù)矩陣:")
print(correlation_matrix)

# 特定變量之間的相關(guān)性
for col1 in df.columns:
    for col2 in df.columns:
        if col1 != col2:
            correlation, p_value = pearsonr(df[col1], df[col2])
            print(f"{col1} 和 {col2} 的相關(guān)系數(shù)為 {correlation:.4f} (p-value={p_value:.4f})")