This is a dataset of Assisted Living, Nursing and Residential Care facilities in Oregon, open as of September, 2016. For each, we have:
Data were munged here.
In [2]:
import pandas as pd
import numpy as np
from IPython.core.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))
In [3]:
df = pd.read_csv('../../data/processed/facilities-3-29-scrape.csv')
In [4]:
df.count()[0]
Out[4]:
Those that have no offline records.
In [10]:
df[(df['offline'].isnull())].count()[0]
Out[10]:
Those that have offline records.
In [11]:
df[(df['offline'].notnull())].count()[0]
Out[11]:
In [12]:
df[(df['offline']>df['online']) & (df['online'].notnull())].count()[0]
Out[12]:
In [13]:
df[(df['online'].isnull()) & (df['offline'].notnull())].count()[0]
Out[13]:
In [14]:
df[(df['online'].notnull()) & (df['offline'].isnull())].count()[0]
Out[14]:
In [15]:
df[(df['online'].notnull()) | df['offline'].notnull()].count()[0]
Out[15]:
In [16]:
df[(df['offline'].isnull())].count()[0]/df.count()[0]*100
Out[16]:
In [17]:
df[df['offline'].notnull()].sum()['fac_capacity']
Out[17]:
In [22]:
df[df['online'].isnull()].count()[0]
Out[22]: