Unsupervised Analysis of Days of week



In [1]:

    
%matplotlib inline
import matplotlib.pyplot as plt
plt.style.use('seaborn')

import pandas as pd
import numpy as np
from sklearn.decomposition import PCA
from sklearn.mixture import GaussianMixture

Get Data



In [2]:

    
from jupyterworkflow.data import get_fremont_data
data = get_fremont_data()
pivoted = data.pivot_table('Total', index = data.index.time, columns = data.index.date)
pivoted.plot(legend = False, alpha = 0.01)









    Out[2]:





<matplotlib.axes._subplots.AxesSubplot at 0x1f298f69eb8>

Principal Component Analysis



In [3]:

    
X = pivoted.fillna(0).T.values
X.shape









    Out[3]:





(1824, 24)



In [4]:

    
X2 = PCA(2).fit_transform(X)
X2.shape









    Out[4]:





(1824, 2)



In [5]:

    
plt.scatter(X2[:, 0], X2[:, 1])









    Out[5]:





<matplotlib.collections.PathCollection at 0x1f29c6bf940>

Unsupervised Clustering



In [6]:

    
gmm = GaussianMixture(2).fit(X)
labels = gmm.predict(X)
labels









    Out[6]:





array([1, 1, 1, ..., 1, 1, 0], dtype=int64)



In [7]:

    
plt.scatter(X2[:, 0], X2[:, 1], c = labels, cmap = 'rainbow')
plt.colorbar()









    Out[7]:





<matplotlib.colorbar.Colorbar at 0x1f29c81ec88>



In [8]:

    
fig, ax = plt.subplots(1, 2, figsize=(14,6))

pivoted.T[labels == 0].T.plot(legend = False, alpha = 0.01, ax=ax[0])
pivoted.T[labels == 1].T.plot(legend = False, alpha = 0.01, ax=ax[1])

ax[0].set_title('Purple Cluster')
ax[1].set_title('Red Cluster')









    Out[8]:





<matplotlib.text.Text at 0x1f29c806cf8>

Comparing with Day of week



In [9]:

    
dayofweek = pd.DatetimeIndex(pivoted.columns).dayofweek
plt.scatter(X2[:, 0], X2[:, 1], c = dayofweek, cmap = 'rainbow')
plt.colorbar()









    Out[9]:





<matplotlib.colorbar.Colorbar at 0x1f2a1985b70>

Analyzing Outliers

The following points are weekdays with a holiday-like pattern



In [10]:

    
dates = pd.DatetimeIndex(pivoted.columns)
dates[(labels == 1) & (dayofweek < 5)]









    Out[10]:





DatetimeIndex(['2012-10-03', '2012-10-04', '2012-10-05', '2012-10-08',
               '2012-10-09', '2012-10-10', '2012-10-11', '2012-10-12',
               '2012-10-15', '2012-10-16',
               ...
               '2017-09-18', '2017-09-19', '2017-09-20', '2017-09-21',
               '2017-09-22', '2017-09-25', '2017-09-26', '2017-09-27',
               '2017-09-28', '2017-09-29'],
              dtype='datetime64[ns]', length=1259, freq=None)