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
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) #we now have a line for each day
Out[2]:
In [3]:
X = pivoted.fillna(0).T.values
X.shape
#24 hours per 1631 days - T transposes
Out[3]:
In [4]:
X2 = PCA(2, svd_solver='full').fit_transform(X)
X2.shape
Out[4]:
In [5]:
plt.scatter(X2[:, 0], X2[:, 1])
#This shows there are two types of days (clustered)
Out[5]:
In [6]:
gmm = GaussianMixture(2).fit(X)
labels = gmm.predict(X)
In [7]:
plt.scatter(X2[:, 0], X2[:, 1], c=labels, cmap='rainbow')
plt.colorbar()
Out[7]:
In [8]:
#Display two charts side by side
fig, ax = plt.subplots(1, 2, figsize=(14,6))
# Show cluster 0
pivoted.T[labels == 0].T.plot(legend=False, alpha=0.1, ax=ax[0]);
# Show cluster 1
pivoted.T[labels == 1].T.plot(legend=False, alpha=0.1, ax=ax[1]);
ax[0].set_title('Purple Cluster')
ax[1].set_title('Red Cluster')
Out[8]:
In [9]:
dayofweek = pd.DatetimeIndex(pivoted.columns).dayofweek
In [10]:
plt.scatter(X2[:, 0], X2[:, 1], c=dayofweek, cmap='rainbow')
plt.colorbar()
Out[10]:
In [11]:
#Non weekends but in the "holidays" (non commute) cluster
#in seattle: 6/2 bad weather, people did not commute
dates = pd.DatetimeIndex(pivoted.columns)
dates[(labels == 1) & (dayofweek < 5)]
Out[11]:
What's up with Feb 6 2017? Snow storm in Seattle.
In [ ]: