In [1]:

    

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

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


    

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);


    

In [3]:

    

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


    

    
Out[3]:





(1610, 24)

In [4]:

    

X2 = PCA(2, svd_solver='full').fit_transform(X)


    

In [5]:

    

X2.shape


    

    
Out[5]:





(1610, 2)

In [6]:

    

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


    

In [7]:

    

gmm = GaussianMixture(2).fit(X)

labels = gmm.predict(X)
labels


    

    
Out[7]:





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

In [8]:

    

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


    

In [9]:

    

fig, ax = plt.subplots(1, 2, figsize=(14, 4))

pivoted.T[labels == 0].T.plot(legend=False, alpha=0.1, ax=ax[0]);
pivoted.T[labels == 1].T.plot(legend=False, alpha=0.1, ax=ax[1]);

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


    

In [10]:

    

dayofweek = pd.DatetimeIndex(pivoted.columns).dayofweek
dayofweek


    

    
Out[10]:





array([2, 3, 4, ..., 6, 0, 1])

In [11]:

    

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


    

In [1]:

    

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


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-1-cb9e4b30ed7d> in <module>()
----> 1 dates = pd.DatetimeIndex(pivoted.columns)
      2 dates[(labels==1) & (dayofweek<5)]

NameError: name 'pd' is not defined