# 定義一個(gè)列表存儲(chǔ)分?jǐn)?shù)
scores = [85, 90, 78, 92, 88]

# 計(jì)算平均值
average_score = sum(scores) / len(scores)

# 打印結(jié)果
print("你的平均分?jǐn)?shù)是:", average_score)

# 導(dǎo)入 statistics 模塊
import statistics

# 定義一個(gè)列表存儲(chǔ)分?jǐn)?shù)
scores = [70, 80, 90, 85, 95]

# 計(jì)算中位數(shù)
median_score = statistics.median(scores)

# 打印結(jié)果
print("你的中位數(shù)分?jǐn)?shù)是:", median_score)

# 導(dǎo)入 statistics 模塊
import statistics

# 定義一個(gè)列表存儲(chǔ)水果偏好
fruits = ["蘋(píng)果", "香蕉", "蘋(píng)果", "橙子", "香蕉"]

# 計(jì)算眾數(shù)
mode_fruit = statistics.mode(fruits)

# 打印結(jié)果
print("最受歡迎的水果是:", mode_fruit)

# 導(dǎo)入 statistics 模塊
import statistics

# 定義一個(gè)列表存儲(chǔ)分?jǐn)?shù)
scores = [75, 80, 85, 90, 100]

# 計(jì)算標(biāo)準(zhǔn)差
std_deviation = statistics.stdev(scores)

# 打印結(jié)果
print("你的考試成績(jī)的標(biāo)準(zhǔn)差是:", std_deviation)

# 導(dǎo)入 pandas 庫(kù)
import pandas as pd

# 定義一個(gè)列表存儲(chǔ)分?jǐn)?shù)
scores = [70, 75, 80, 85, 90, 75, 95, 85, 80, 70]

# 創(chuàng)建 DataFrame
df = pd.DataFrame(scores, columns=['Score'])

# 生成頻率分布表
frequency_table = df.value_counts(bins=5)  # 將分?jǐn)?shù)分為 5 個(gè)區(qū)間

# 打印結(jié)果
print("頻率分布表:\n", frequency_table)

# 導(dǎo)入 matplotlib 庫(kù)
import matplotlib.pyplot as plt

# 定義一個(gè)列表存儲(chǔ)步數(shù)
steps = [3000, 5000, 7000, 8000, 12000, 4000, 6000]

# 繪制直方圖
plt.hist(steps, bins=5, color='skyblue', edgecolor='black')
plt.title('每日步數(shù)分布')
plt.xlabel('步數(shù)')
plt.ylabel('天數(shù)')
plt.show()

# 導(dǎo)入 numpy 和 scipy.stats 庫(kù)
import numpy as np
from scipy import stats

# 定義學(xué)習(xí)時(shí)間和成績(jī)
study_time = [1, 2, 3, 4, 5]  # 學(xué)習(xí)小時(shí)數(shù)
scores = [50, 60, 65, 80, 90]  # 對(duì)應(yīng)的分?jǐn)?shù)

# 計(jì)算相關(guān)系數(shù)
correlation_coefficient, p_value = stats.pearsonr(study_time, scores)

# 打印結(jié)果
print("學(xué)習(xí)時(shí)間與成績(jī)之間的相關(guān)系數(shù)是:", correlation_coefficient)

# 導(dǎo)入 scipy.stats 庫(kù)
from scipy import stats

# 定義兩組分?jǐn)?shù)
method_a_scores = [80, 85, 90, 95, 100]
method_b_scores = [75, 80, 85, 90, 95]

# 進(jìn)行 t 檢驗(yàn)
t_statistic, p_value = stats.ttest_ind(method_a_scores, method_b_scores)

# 打印結(jié)果
print("t 檢驗(yàn)結(jié)果: t 統(tǒng)計(jì)量 =", t_statistic, ", p 值 =", p_value)

# 導(dǎo)入 sklearn 庫(kù)
from sklearn.linear_model import LinearRegression
import numpy as np

# 定義廣告支出和銷(xiāo)售額
advertising_spent = np.array([1000, 2000, 3000, 4000, 5000]).reshape(-1, 1)
sales = np.array([15000, 25000, 35000, 45000, 55000])

# 創(chuàng)建線性回歸模型并訓(xùn)練
model = LinearRegression()
model.fit(advertising_spent, sales)

# 打印回歸系數(shù)
print("線性回歸系數(shù) (廣告支出與銷(xiāo)售額):", model.coef_[0])

# 導(dǎo)入 pandas 庫(kù)
import pandas as pd

# 創(chuàng)建 DataFrame 包含用戶信息
data = {
    '姓名': ['Alice', 'Bob', 'Charlie', 'David'],
    '年齡': [25, None, 30, 35],
    '城市': ['北京', '上海', '廣州', '深圳']
}
df = pd.DataFrame(data)

# 去除缺失年齡的行
cleaned_df = df.dropna(subset=['年齡'])

# 打印清洗后的數(shù)據(jù)
print("清洗后的用戶信息:\n", cleaned_df)