深入解析 Python 数据分析库：从基础到高级应用

import numpy as np

# 创建一个一维数组
arr = np.array([1, 2, 3, 4])
print(arr)

# 创建一个二维数组
arr2d = np.array([[1, 2], [3, 4]])
print(arr2d)

arr1 = np.array([1, 2, 3])
arr2 = np.array([4, 5, 6])
result = arr1 + arr2  # 数组加法
print(result)

# 矩阵乘法
A = np.array([[1, 2], [3, 4]])
B = np.array([[5, 6], [7, 8]])
result = np.dot(A, B)
print(result)

import pandas as pd

# 从字典创建 DataFrame
data = {'Name': ['Alice', 'Bob', 'Charlie'], 'Age': [24, 27, 22]}
df = pd.DataFrame(data)
print(df)

# 从 CSV 文件读取数据
df = pd.read_csv('data.csv')
print(df.head())

# 删除缺失值
df.dropna(inplace=True)

# 填充缺失值
df.fillna(0, inplace=True)

# 数据筛选
filtered_df = df[df['Age'] > 25]
print(filtered_df)

grouped_df = df.groupby('Age').mean()
print(grouped_df)

import matplotlib.pyplot as plt

# 绘制折线图
x = [1, 2, 3, 4, 5]
y = [1, 4, 9, 16, 25]
plt.plot(x, y)
plt.xlabel('x')
plt.ylabel('y')
plt.title('Simple Line Plot')
plt.show()

import seaborn as sns

# 绘制箱型图
sns.boxplot(x='Age', y='Name', data=df)
plt.show()

from scipy import stats

# 正态分布的概率密度函数
x = np.linspace(-5, 5, 100)
y = stats.norm.pdf(x, 0, 1)

plt.plot(x, y)
plt.title('Normal Distribution')
plt.show()

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
scaled_data = scaler.fit_transform(df[['Age']])

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 数据分割
X_train, X_test, y_train, y_test = train_test_split(df[['Age']], df['Name'], test_size=0.2)

# 训练模型
model = LogisticRegression()
model.fit(X_train, y_train)

# 预测并评估
y_pred = model.predict(X_test)
print(accuracy_score(y_test, y_pred))

import statsmodels.api as sm

# 线性回归
X = df[['Age']]
X = sm.add_constant(X)
y = df['Name']
model = sm.OLS(y, X).fit()

print(model.summary())

# 读取数据
df = pd.read_csv('sales_data.csv')

# 数据清洗和预处理
df['Date'] = pd.to_datetime(df['Date'])
df.fillna(0, inplace=True)

# 数据可视化
sns.lineplot(x='Date', y='Sales', data=df)
plt.title('Sales Trend Over Time')
plt.show()

# 建立回归模型预测销售
from sklearn.linear_model import LinearRegression
X = df[['Date']].values  # 时间特征
y = df['Sales'].values  # 销售量

model = LinearRegression()
model.fit(X, y)

# 预测未来销售趋势
future_dates = pd.date_range(start='2025-01-01', periods=30, freq='D')
predictions = model.predict(future_dates.values.reshape(-1, 1))

# 可视化预测结果
plt.plot(future_dates, predictions, label='Predicted Sales')
plt.legend()
plt.show()