Scatter plots in Python

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 'NSE' not in symbols:  # add SPY for reference, if absent
        symbols.insert(0, 'NSE')

    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 == 'NSE':  # drop dates SPY did not trade
            df = df.dropna(subset=["NSE"])

    return df


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

def compute_daily_returns(df):
    daily_returns = df.copy()
    # Compute daily rerurns for row 1 onwards
    #daily_returns[1:] = (df[1:] / df[:-1].values) -1
    daily_returns = (df / df.shift(1)) -1
    daily_returns.ix[0, :] = 0 #set daily returns for row 0 to 0
    return daily_returns


def plot_histogram(daily_returns):
    daily_returns.hist(bins=20)
    mean = daily_returns.mean()
    std = daily_returns.std()

    plt.axvline(x=mean, color='r', linestyle='--')
    plt.axvline(x=std, color='k', linestyle='--')
    plt.axvline(x=-std, color='k', linestyle='--')

    plt.show()


def test_run():
    dates = pd.date_range('2014-01-01', '2014-12-31')
    symbols = ['NSE', 'HDFCBANK', 'ITC']
    df = get_data(symbols, dates)

    daily_returns = compute_daily_returns(df)

    daily_returns.plot(kind='scatter', x='NSE', y='HDFCBANK')
    beta_hdfcbank, aplha_hdfcbank = np.polyfit(daily_returns['NSE'], daily_returns['HDFCBANK'],1)
    plt.plot(daily_returns['NSE'], beta_hdfcbank*daily_returns['NSE'] + aplha_hdfcbank, '-', color='r')
    print("beta_hdfc", beta_hdfcbank)
    print("aplha_hdfc", aplha_hdfcbank)
    plt.show()

    daily_returns.plot(kind='scatter', x='NSE', y='ITC')
    beta_itc, aplha_itc = np.polyfit(daily_returns['NSE'], daily_returns['ITC'], 1)
    plt.plot(daily_returns['NSE'], beta_itc * daily_returns['NSE'] + aplha_itc, '-', color='r')
    print("beta_itc", beta_itc)
    print("alpha_itc", aplha_itc)
    plt.show()

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


if __name__ == "__main__":
    test_run()

Scatter plot

(Visited 167 times, 1 visits today)

Leave a Reply

Your email address will not be published. Required fields are marked *

Solve : *
18 ⁄ 6 =