def scatterplots():
#Read data
dates = pd.date_range('2009-01-01', '2012-12-31')
symbols = ['SPY', 'XOM', 'GLD']
df = get_data(symbols, dates)
#Compute daily returns
daily_returns = compute_daily_returns(df)
# Scatterplot SPY vs 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()
# Scatterplot SPY vs 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()
#Calculate correlation coefficient
print(daily_returns.corr(method='pearson'))
def histogram_statistics():
#Read data
dates = pd.date_range('2009-01-01', '2012-12-31')
symbols = ['SPY']
df = get_data(symbols, dates)
plot_data(df)
#Compute daily returns
daily_returns = compute_daily_returns(df)
plot_data(daily_returns, title="Daily returns", ylabel="Daily returns")
#Plot a histogram
daily_returns.hist(bins=20) #changing no. of bins to 20
# plt.show()
#Get mean and standard deviation
mean = daily_returns['SPY'].mean()
print("mean =", mean)
std = daily_returns['SPY'].std()
print("std =", 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()
#Compute kurtosis
print(daily_returns.kurtosis())
def bollinger_bands():
"""Bollinger Bands."""
# Read data
dates = pd.date_range('2012-01-01', '2012-12-31')
symbols = ['SPY']
df = get_data(symbols, dates)
# Compute Bollinger Bands
# 1. Compute rolling mean
rm_SPY = get_rolling_mean(df['SPY'], window=20)
# 2. Compute rolling standard deviation
rstd_SPY = get_rolling_std(df['SPY'], window=20)
# 3. Compute upper and lower bands
upper_band, lower_band = get_bollinger_bands(rm_SPY, rstd_SPY)
# Plot raw SPY values, rolling mean and Bollinger Bands
ax = df['SPY'].plot(title="Bollinger Bands", label='SPY')
rm_SPY.plot(label='Rolling mean', ax=ax)
upper_band.plot(label='upper band', ax=ax)
lower_band.plot(label='lower band', ax=ax)
# Add axis labels and legend
ax.set_xlabel("Date")
ax.set_ylabel("Price")
ax.legend(loc='upper left')
plt.show()
def compute_daily_returns_run():
# Read data
dates = pd.date_range('2012-07-01', '2012-07-31') # one month only
symbols = ['SPY', 'XOM']
df = get_data(symbols, dates)
plot_data(df)
# Compute daily returns
daily_returns = compute_daily_returns(df)
plot_data(daily_returns, title="Daily returns", ylabel="Daily returns")
def compute_statistics():
# Read data
dates = pd.date_range('2010-01-01', '2012-12-31')
symbols = ['SPY', 'XOM', 'GOOG', 'GLD']
df = get_data(symbols, dates)
plot_data(df)
# Compute global statistics for each stock
print(df.mean())
print(df.median())
print(df.std())
def plot_multiple_histograms():
#Read data
dates = pd.date_range('2009-01-01', '2012-12-31')
symbols = ['SPY', 'XOM']
df = get_data(symbols, dates)
plot_data(df)
#Compute daily returns
daily_returns = compute_daily_returns(df)
plot_data(daily_returns, title="Daily returns", ylabel="Daily returns")
#Plot histogram directly from dataframe
# daily_returns.hist(bins=20)
# plt.show()
#Compute and plot both histograms 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()
def rolling_mean():
# Read data
dates = pd.date_range('2012-01-01', '2012-12-31')
symbols = ['SPY']
df = get_data(symbols, dates)
# Plot SPY data, retain matplotlib axis object
ax = df['SPY'].plot(title="SPY rolling mean", label='SPY')
# Compute rolling mean using a 20-day window
# deprecated -> rm_SPY = pd.rolling_mean(df['SPY'], window=20)
rm_SPY = df['SPY'].rolling(window=20, center=False).mean()
# Add rolling mean to same plot
rm_SPY.plot(label='Rolling mean', ax=ax)
# Add acis labels and legend
ax.set_xlabel("Date")
ax.set_ylabel("Price")
ax.legend(loc='upper left')
plt.show()
import matplotlib.pyplot as plt
def plot(df_data):
ax = df_data.plot(title="Incomplete Data", fontsize=2)
ax.set_xlabel("Date")
ax.set_ylabel("Price")
plt.show()
def fill_missing_values(df_data):
"""Fill missing values in data frame, in place."""
df_data.fillna(method="ffill", inplace=True)
df_data.fillna(method="bfill", inplace=True)
if __name__ == '__main__':
#list of symbols
symbollist = ["PSX", "FAKE1", "FAKE2"]
#symbollist=["FAKE2"]
#create date range
dates = pd.date_range('2005-12-31', '2014-12-07')
#get adjusted close of each symbol
df_data = get_data(symbollist, dates)
# Fill missing values
fill_missing_values(df_data)
# Plot
plot(df_data)