Heatmap Example¶

import numpy as np
import pandas as pd
from scipy import stats
from pytz import timezone
import matplotlib.pyplot as plt
import seaborn as sns

data_cached = get_pricing(['SPY','SH'], start_date='2014-03-27', end_date='2015-03-27',
                          fields='volume', frequency='minute').dropna()

data = data_cached.copy(deep=True)

def day_of_year(dt):   # Day of year (1-366) for a datetime
    return dt.timetuple().tm_yday

def minute_of_day(dt): # Minute of day (0-1439) for a datetime
    return (dt.hour * 60) + dt.minute

data['day_of_year'] = np.vectorize(day_of_year)(data.index.date)
data['minute_of_day'] = np.vectorize(minute_of_day)(data.index.tz_convert(timezone('US/Eastern')).time)

data.tail()

MINUTES_PER_MARKET_DAY = 390
volumes = data.iloc[:, 0:2]
means = volumes.apply(lambda x: pd.rolling_mean(x, window=MINUTES_PER_MARKET_DAY))
sds = volumes.apply(lambda x: pd.rolling_std(x, window=MINUTES_PER_MARKET_DAY))
zs = ((volumes - means) / sds)
data['z_diff'] = zs.iloc[:, 1] - zs.iloc[:, 0]
data.tail()

ht_map = pd.pivot_table(data,'z_diff',index=data['day_of_year'], columns=data['minute_of_day'],fill_value=0)
plt.pcolor(ht_map, cmap='coolwarm')
plt.colorbar()
plt.clim(ht_map.min().min(),ht_map.max().max())

def reduce_tick_labels(labels, n):  # Keep every nth label, replace others by space
    kept = labels[::n]
    reduced = ['' for label in labels]
    reduced[::n] = kept
    return reduced

MINUTES_PER_HOUR = 60
DAYS_PER_MONTH = 30  # approximately
xticks = reduce_tick_labels(ht_map.columns, MINUTES_PER_HOUR)
yticks = reduce_tick_labels(ht_map.index, DAYS_PER_MONTH)

sns.heatmap(ht_map, linewidths=0, xticklabels=xticks, yticklabels=yticks)