import pandas
import pylab

df_total_watt = pandas.read_table('../../data/total_watt.csv', sep=',', header=None, names=['datetime', 'consumption' ], parse_dates=['datetime'])

df_total_watt

df_total_watt.head()

df_total_watt.consumption.describe()

pylab.plot(df_total_watt.datetime, df_total_watt.consumption)
pylab.ylabel('consumption (Wh)')
pylab.xlabel('time')
pylab.title('energy consumption per 30mins')

pylab.plot(df_total_watt.datetime, df_total_watt.consumption.diff())
pylab.ylabel('consumption change (Wh)')
pylab.xlabel('time')
pylab.title('energy consumption change per 30mins')

df_total_watt['date'] = [dt.date() for dt in df_total_watt['datetime']]
df_total_watt_daily = df_total_watt.groupby('date').sum().reset_index()

df_total_watt_daily.head()

pylab.bar(df_total_watt_daily.date, df_total_watt_daily.consumption)
pylab.ylabel('consumption(Wh)')
pylab.xlabel('date')
pylab.title('energy consumption per day')

df_total_watt_daily.consumption.describe()

count = {}
interval = 5000
consumption_ranges = range(0,70000,interval)
for consumption_range in consumption_ranges:
    count[consumption_range] = \
    df_total_watt_daily[df_total_watt_daily['consumption'] >= consumption_range].consumption.count() - \
    df_total_watt_daily[df_total_watt_daily['consumption'] >= consumption_range + interval].consumption.count()
    
pylab.bar(count.keys(), count.values(), width=interval)
pylab.ylabel('frequency (days)')
pylab.xlabel('total consumption per day (kWh)')
pylab.title('distribution of energy consumption per day')

df_total_watt_daily_high = df_total_watt_daily[df_total_watt_daily.consumption > df_total_watt_daily.consumption.mean() + df_total_watt_daily.consumption.std()]

df_total_watt_daily_low = df_total_watt_daily[df_total_watt_daily.consumption < df_total_watt_daily.consumption.mean() - df_total_watt_daily.consumption.std()]

df_total_watt_daily_middle = df_total_watt_daily[df_total_watt_daily.consumption <= df_total_watt_daily.consumption.mean() + df_total_watt_daily.consumption.std()]
df_total_watt_daily_middle = df_total_watt_daily_middle[df_total_watt_daily_middle.consumption >= df_total_watt_daily.consumption.mean() - df_total_watt_daily.consumption.std()]

df_total_watt_daily_low

df_total_watt_daily_high

df_total_watt_daily_middle.head()

middle = pylab.bar(df_total_watt_daily_middle.date, df_total_watt_daily_middle.consumption, color='green')
high = pylab.bar(df_total_watt_daily_high.date, df_total_watt_daily_high.consumption, color='red')
low = pylab.bar(df_total_watt_daily_low.date, df_total_watt_daily_low.consumption, color='blue')
pylab.ylabel('energy consumption per day (Wh)')
pylab.xlabel('date')
pylab.title('clustered energy consumption per day')
pylab.legend((middle, high, low), ('middle','high', 'low'))

pylab.bar(range(df_total_watt_daily.consumption.count()),df_total_watt_daily.sort('consumption')['consumption'])
pylab.ylabel('energy consumption per day (Wh)')
pylab.xlabel('order')
pylab.title('energy consumption per day ordered by consumption')

pylab.bar(range(df_total_watt_daily.consumption.count()),df_total_watt_daily.sort('consumption')['consumption'],
log = True)
pylab.ylabel('energy consumption per day (Wh)')
pylab.xlabel('order')
pylab.title('energy consumption per day ordered by consumption')

df_total_watt_daily['consumption_log'] = df_total_watt_daily.consumption.map(lambda c: log(c))

df_total_watt_daily['consumption_log'].describe()

df_total_watt_daily_log_high = df_total_watt_daily[df_total_watt_daily['consumption_log'] > df_total_watt_daily['consumption_log'].mean() + df_total_watt_daily['consumption_log'].std()]
df_total_watt_daily_log_low = df_total_watt_daily[df_total_watt_daily['consumption_log'] < df_total_watt_daily['consumption_log'].mean() - df_total_watt_daily['consumption_log'].std()]
df_total_watt_daily_log_middle = df_total_watt_daily[df_total_watt_daily['consumption_log'] <= df_total_watt_daily['consumption_log'].mean() + df_total_watt_daily['consumption_log'].std()]
df_total_watt_daily_log_middle = df_total_watt_daily_log_middle[df_total_watt_daily_log_middle['consumption_log'] >= df_total_watt_daily['consumption_log'].mean() - df_total_watt_daily['consumption_log'].std()]

middle = pylab.bar(df_total_watt_daily_log_middle.date, df_total_watt_daily_log_middle.consumption, color='green')
high = pylab.bar(df_total_watt_daily_log_high.date, df_total_watt_daily_log_high.consumption, color='red')
low = pylab.bar(df_total_watt_daily_log_low.date, df_total_watt_daily_log_low.consumption, color='blue')
pylab.ylabel('energy consumption per day (Wh)')
pylab.xlabel('date')
pylab.title('clustered energy consumption per day')
pylab.legend((middle, high, low), ('middle','high', 'low'))

from scipy.cluster.vq import kmeans2, whiten

whitened = whiten(df_total_watt_daily.consumption.values)
initial_centroids = numpy.array([numpy.percentile(whitened,25),numpy.percentile(whitened,50),numpy.percentile(whitened,75)])
centroids, labels = kmeans2((whitened),initial_centroids)

centroids, labels

df_total_watt_daily['labels'] = labels

df_total_watt_daily_cluster_low = df_total_watt_daily[df_total_watt_daily['labels'] == 0]
df_total_watt_daily_cluster_middle = df_total_watt_daily[df_total_watt_daily['labels'] == 1]
df_total_watt_daily_cluster_high = df_total_watt_daily[df_total_watt_daily['labels'] == 2]

low = pylab.bar(df_total_watt_daily_cluster_low.date, df_total_watt_daily_cluster_low.consumption, color='blue')
middle = pylab.bar(df_total_watt_daily_cluster_middle.date, df_total_watt_daily_cluster_middle.consumption, color='green')
high = pylab.bar(df_total_watt_daily_cluster_high.date, df_total_watt_daily_cluster_high.consumption, color='red')
pylab.ylabel('energy consumption per day (Wh)')
pylab.xlabel('date')
pylab.title('clustered energy consumption per day')
pylab.legend((middle, high, low), ('middle','high', 'low'))