Python入门（14）--数据分析基础

Python数据分析基础 📊

1. NumPy基础操作 🔢

1.1 NumPy数组创建与操作

NumPy是Python中科学计算的基础库，提供了高效的多维数组对象和处理工具：

python">import numpy as np# 创建数组
arr1 = np.array([1, 2, 3, 4, 5])
arr2 = np.zeros((3, 4))  # 3x4的零矩阵
arr3 = np.ones((2, 3))   # 2x3的1矩阵
arr4 = np.arange(0, 10, 2)  # [0,2,4,6,8]# 数组操作
arr = np.array([[1, 2, 3], [4, 5, 6]])
print(arr.shape)    # 形状：(2, 3)
print(arr.dtype)    # 数据类型
print(arr.size)     # 元素总数
print(arr.ndim)     # 维度数# 数组计算
arr_sum = arr1 + arr1  # 元素级加法
arr_mul = arr1 * 2     # 标量乘法
dot_product = np.dot(arr1, arr1)  # 点积

1.2 数组切片与索引

python">arr = np.array([[1, 2, 3, 4],[5, 6, 7, 8],[9, 10, 11, 12]])# 基本切片
print(arr[0, :])    # 第一行
print(arr[:, 1])    # 第二列
print(arr[0:2, 1:3])  # 子矩阵# 布尔索引
mask = arr > 5
print(arr[mask])    # 输出大于5的元素

1.3 数组运算与统计

python">arr = np.array([[1, 2, 3], [4, 5, 6]])# 基本运算
print(np.sum(arr))          # 求和
print(np.mean(arr))         # 平均值
print(np.std(arr))          # 标准差
print(np.var(arr))          # 方差# 按轴运算
print(np.sum(arr, axis=0))  # 按列求和
print(np.sum(arr, axis=1))  # 按行求和

2. Pandas数据处理 🐼

2.1 Series和DataFrame基础

python">import pandas as pd# 创建Series
s = pd.Series([1, 3, 5, np.nan, 6, 8])# 创建DataFrame
df = pd.DataFrame({'A': [1, 2, 3, 4],'B': pd.date_range('20230101', periods=4),'C': pd.Series(1, index=list(range(4))),'D': np.random.randn(4)
})# 基本属性
print(df.shape)     # 形状
print(df.dtypes)    # 数据类型
print(df.index)     # 索引
print(df.columns)   # 列名

2.2 数据清洗与处理

python"># 处理缺失值
df.fillna(value=0)           # 填充缺失值
df.dropna(how='any')         # 删除含有缺失值的行# 数据转换
df['A'] = df['A'].astype('float64')  # 类型转换
df['B'] = pd.to_datetime(df['B'])    # 转换为日期类型# 数据筛选
mask = df['A'] > 2
filtered_df = df[mask]       # 条件筛选# 数据排序
df.sort_values('A', ascending=False)  # 按A列降序排序

2.3 数据聚合与分组操作

python"># 分组操作
grouped = df.groupby('A')
print(grouped.mean())        # 分组平均值
print(grouped.count())       # 分组计数# 聚合操作
agg_funcs = {'B': 'count','C': ['sum', 'mean'],'D': ['min', 'max']
}
result = df.groupby('A').agg(agg_funcs)

3. Matplotlib数据可视化 📈

3.1 基础绘图

python">import matplotlib.pyplot as plt# 线图
plt.figure(figsize=(10, 6))
plt.plot([1, 2, 3, 4], [1, 4, 2, 3])
plt.title('Simple Line Plot')
plt.xlabel('X axis')
plt.ylabel('Y axis')
plt.grid(True)
plt.show()# 散点图
plt.scatter(df['A'], df['D'])
plt.title('Scatter Plot')
plt.show()

3.2 高级绘图

python"># 子图
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4))ax1.plot(df['A'], df['B'])
ax1.set_title('Plot 1')ax2.scatter(df['C'], df['D'])
ax2.set_title('Plot 2')plt.tight_layout()
plt.show()# 直方图
plt.hist(df['D'], bins=20)
plt.title('Histogram')
plt.show()

4. 实战案例：股票数据分析 📊

让我们创建一个完整的股票数据分析系统：

python">import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from datetime import datetime, timedelta
import yfinance as yfclass StockAnalyzer:"""股票数据分析类"""def __init__(self, symbol: str, start_date: str, end_date: str):self.symbol = symbolself.start_date = start_dateself.end_date = end_dateself.data = Noneself._load_data()def _load_data(self):"""加载股票数据"""try:self.data = yf.download(self.symbol, start=self.start_date, end=self.end_date)except Exception as e:raise Exception(f"加载股票数据失败：{str(e)}")def calculate_technical_indicators(self):"""计算技术指标"""# 移动平均线self.data['MA5'] = self.data['Close'].rolling(window=5).mean()self.data['MA20'] = self.data['Close'].rolling(window=20).mean()# RSI指标delta = self.data['Close'].diff()gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()loss = (-delta.where(delta < 0, 0)).rolling(window=14).mean()rs = gain / lossself.data['RSI'] = 100 - (100 / (1 + rs))# MACD指标exp1 = self.data['Close'].ewm(span=12, adjust=False).mean()exp2 = self.data['Close'].ewm(span=26, adjust=False).mean()self.data['MACD'] = exp1 - exp2self.data['Signal'] = self.data['MACD'].ewm(span=9, adjust=False).mean()return self.datadef plot_stock_analysis(self):"""绘制股票分析图表"""# 创建子图fig = plt.figure(figsize=(15, 10))# 价格和成交量图ax1 = plt.subplot2grid((4, 1), (0, 0), rowspan=2)ax2 = plt.subplot2grid((4, 1), (2, 0))ax3 = plt.subplot2grid((4, 1), (3, 0))# 绘制价格和移动平均线ax1.plot(self.data.index, self.data['Close'], label='Close')ax1.plot(self.data.index, self.data['MA5'], label='MA5')ax1.plot(self.data.index, self.data['MA20'], label='MA20')ax1.set_title(f'{self.symbol} Stock Analysis')ax1.set_ylabel('Price')ax1.legend()ax1.grid(True)# 绘制成交量ax2.bar(self.data.index, self.data['Volume'])ax2.set_ylabel('Volume')ax2.grid(True)# 绘制MACDax3.plot(self.data.index, self.data['MACD'], label='MACD')ax3.plot(self.data.index, self.data['Signal'], label='Signal')ax3.set_ylabel('MACD')ax3.legend()ax3.grid(True)plt.tight_layout()return figdef generate_trading_signals(self):"""生成交易信号"""signals = pd.DataFrame(index=self.data.index)signals['signal'] = 0# MACD交叉信号signals['signal'] = np.where(self.data['MACD'] > self.data['Signal'], 1, 0)signals['position'] = signals['signal'].diff()return signalsdef calculate_returns(self):"""计算收益率统计"""daily_returns = self.data['Close'].pct_change()stats = {'Total Return': (self.data['Close'][-1] / self.data['Close'][0] - 1) * 100,'Average Daily Return': daily_returns.mean() * 100,'Daily Return Std': daily_returns.std() * 100,'Sharpe Ratio': (daily_returns.mean() / daily_returns.std()) * np.sqrt(252),'Max Drawdown': ((self.data['Close'] / self.data['Close'].cummax() - 1).min()) * 100}return pd.Series(stats)def main():"""主函数：演示股票分析系统的使用"""# 创建分析器实例analyzer = StockAnalyzer(symbol='AAPL',start_date='2023-01-01',end_date='2023-12-31')try:# 计算技术指标analyzer.calculate_technical_indicators()# 生成交易信号signals = analyzer.generate_trading_signals()# 计算收益统计returns = analyzer.calculate_returns()print("\n收益率统计：")print(returns)# 绘制分析图表fig = analyzer.plot_stock_analysis()plt.show()except Exception as e:print(f"分析过程出错：{str(e)}")if __name__ == "__main__":main()