2. Finance data with python

01-06 直方图和散点图

在处理金融领域的数据时，需要进行一些统计量的统计。

常见的就是对日收益回报进行可视化分析，

1.可将日收益回报进行直方图的绘制(histogram),并求其平均值、标准差、峰度、散点图、拟合直线、不同股票之间的相关性。

主要任务有：

1）针对现有的一支股票的数据，进行价格曲线的可视化、日收益回报曲线的刻画，相应直方图、均值、左右2的标准差范围的非可视化、峰度计算

2）两支股票甚至多支股票的价格曲线的可视化、相应日收益回报的直方图可视化在同一坐标轴中

3）以SPY股票作为基准股票数据，比较其和XOM和GLD两支股票的情况：可视化关系的散点图，利用np.ployfit函数进行拟合直线的求解，得到相应的系数项和常数项，可视化相应的拟合直线；直接根据原始的日收益回报数据得到相应的相关系数值。

"""Slice and plot"""

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


def symbol_to_path(symbol, base_dir="data"):
    """Return CSV file path given ticker symbol."""
    return os.path.join(base_dir, "{}.csv".format(str(symbol)))


def get_data(symbols, dates):
    """Read stock data (adjusted close) for given symbols from CSV files."""
    df = pd.DataFrame(index=dates)
    if 'SPY' not in symbols:  # add SPY for reference, if absent
        symbols.insert(0, 'SPY')

    for symbol in symbols:
        df_temp = pd.read_csv(symbol_to_path(symbol), index_col='Date',
                              parse_dates=True, usecols=['Date', 'Adj Close'], na_values=['nan'])
        df_temp = df_temp.rename(columns={'Adj Close': symbol})
        df = df.join(df_temp)
        if symbol == 'SPY':  # drop dates SPY did not trade
            df = df.dropna(subset=["SPY"])

    return df


def plot_data(df, title="Stock prices", ylabel, xlabel):
    """Plot stock prices with a custom title and meaningful axis labels."""
    ax = df.plot(title=title, fontsize=12)
    ax.set_xlabel(xlabel)
    ax.set_ylabel(ylabel)
    plt.show()

def compute_daily_returns(df):
    """compute and return the daily return values."""
    daily_returns = df.copy()
    daily_returns[1:] = (df[1:]/df[:-1].values) - 1
    daily_returns.ix[0, :] = 0
    return daily_returns

# 对于一只股票的数据进行价格可视化，日收益回报的直方图、mean、std可视化。
def test_run1():
    dates = pd.date_range('2010-01-01', '2010-12-31')

    # Choose stock symbols to read
    symbols = ['SPY']  # SPY will be added in get_data()

    # Get stock data
    df = get_data(symbols, dates)
    plot_data(df, title='prince', ylabel='price',xlabel='Date')

    # compute daily returns
    daily_returns = compute_daily_returns(df)
    plot_data(daily_returns, title='Daily Returns', ylabel='Daily returns',xlabel='Date')

    # plot a histogram
    daily_returns.hist(bins=20) # 直方图中有bins个基础块。

    # Get mean and standard deviation
    mean = daily_returns['SPY'].mean()
    print('mean:', mean)
    std = daily_returns['SPY'].std()
    print('std:', std)

    # plot mean and std
    plt.axvline(mean, color='w', linestyle='dashed', linewidth=2)
    plt.axvline(std, color='r', linestyle='dashed', linewidth=2)
    plt.axvline(-std, color='r', linestyle='dashed', linewidth=2)
    plt.show()

    # Get kurtosis
    kurtosis = daily_returns.kurtosis()
    print('kurtosis:', kurtosis)

# 将多支股票的日收益回报直方图放在一张图中。
def test_run2():
    # Define a date range
    dates = pd.date_range('2010-01-01', '2010-12-31')

    # Choose stock symbols to read
    symbols = ['SPY', 'XOM']  # SPY will be added in get_data()

    # Get stock data
    df = get_data(symbols, dates)

    # compute daily returns
    daily_returns = compute_daily_returns(df)
    
    # compute and plot both histogram on the same chart
    daily_returns['SPY'].hist(bins=20, label='SPY')
    daily_returns['XOM'].hist(bins=20, label='XOM')
    plt.legend(loc='upper right')
    plt.show()


# 根据日收益回报，以SPY为基准数据，分别画出SPY&XOM 和 SPY&GLD的散点图，并进行相应的直线拟合，然后可视化相应的拟合直线。
# 最后计算统计出的日收益回报数据中的几支股票的相关性分析。
def test_run3():
    # Define a date range
    dates = pd.date_range('2010-01-01', '2010-12-31')

    # Choose stock symbols to read
    symbols = ['SPY', 'XOM', 'GLD']  # SPY will be added in get_data()

    # Get stock data
    df = get_data(symbols, dates)

    # compute daily returns
    daily_returns = compute_daily_returns(df)

    # scatter SPY and XOM
    daily_returns.plot(kind='scatter', x='SPY', y='XOM')
    beta_XOM, alpha_XOM = np.polyfit(daily_returns['SPY'], daily_returns['XOM'], 1)
    print('beta_XOM:', beta_XOM)
    print('alpha_XOM:', alpha_XOM)
    plt.plot(daily_returns['SPY'], beta_XOM*daily_returns['SPY']+alpha_XOM, '-', color='r')
    plt.show()

    # scatter SPY and GLD
    daily_returns.plot(kind='scatter', x='SPY', y='GLD')
    beta_GLD, alpha_GLD = np.polyfit(daily_returns['SPY'], daily_returns['GLD'], 1)
    print('beta_GLD:', beta_GLD)
    print('alpha_GLD:', alpha_GLD)
    plt.plot(daily_returns['SPY'], beta_GLD * daily_returns['SPY'] + alpha_GLD, '-', color='r')
    plt.show()

    print(daily_returns.corr(method='pearson'))

if __name__ == "__main__":
    test_run1()
    test_run2()
    test_run3()