import numpy as np
import pandas as pd
import seaborn as sns
sns.set(color_codes=True)
import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline
import os
import time
# random state
SEED = 0
RNG = np.random.RandomState(SEED)
import pandas_profiling
# Jupyter notebook settings for pandas
pd.set_option('display.max_columns', 100)
# pd.set_option('display.float_format', '{:,.4g}'.format) # numbers sep by comma
pd.set_option('display.max_rows', 100) # None for all the rows
pd.set_option('display.max_colwidth', 200)
print([(x.__name__,x.__version__) for x in [np, pd,sns,matplotlib,pandas_profiling]])
[('numpy', '1.16.4'), ('pandas', '0.25.0'), ('seaborn', '0.9.0'), ('matplotlib', '3.1.1'), ('pandas_profiling', '2.3.0')]
df = pd.read_csv('../data/raw/kc_house_data.csv')
df.head()
| id | date | price | bedrooms | bathrooms | sqft_living | sqft_lot | floors | waterfront | view | condition | grade | sqft_above | sqft_basement | yr_built | yr_renovated | zipcode | lat | long | sqft_living15 | sqft_lot15 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 7129300520 | 20141013T000000 | 221900.0 | 3 | 1.00 | 1180 | 5650 | 1.0 | 0 | 0 | 3 | 7 | 1180 | 0 | 1955 | 0 | 98178 | 47.5112 | -122.257 | 1340 | 5650 |
| 1 | 6414100192 | 20141209T000000 | 538000.0 | 3 | 2.25 | 2570 | 7242 | 2.0 | 0 | 0 | 3 | 7 | 2170 | 400 | 1951 | 1991 | 98125 | 47.7210 | -122.319 | 1690 | 7639 |
| 2 | 5631500400 | 20150225T000000 | 180000.0 | 2 | 1.00 | 770 | 10000 | 1.0 | 0 | 0 | 3 | 6 | 770 | 0 | 1933 | 0 | 98028 | 47.7379 | -122.233 | 2720 | 8062 |
| 3 | 2487200875 | 20141209T000000 | 604000.0 | 4 | 3.00 | 1960 | 5000 | 1.0 | 0 | 0 | 5 | 7 | 1050 | 910 | 1965 | 0 | 98136 | 47.5208 | -122.393 | 1360 | 5000 |
| 4 | 1954400510 | 20150218T000000 | 510000.0 | 3 | 2.00 | 1680 | 8080 | 1.0 | 0 | 0 | 3 | 8 | 1680 | 0 | 1987 | 0 | 98074 | 47.6168 | -122.045 | 1800 | 7503 |
df.describe()
| id | price | bedrooms | bathrooms | sqft_living | sqft_lot | floors | waterfront | view | condition | grade | sqft_above | sqft_basement | yr_built | yr_renovated | zipcode | lat | long | sqft_living15 | sqft_lot15 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 2.161300e+04 | 2.161300e+04 | 21613.000000 | 21613.000000 | 21613.000000 | 2.161300e+04 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 | 21613.000000 |
| mean | 4.580302e+09 | 5.400881e+05 | 3.370842 | 2.114757 | 2079.899736 | 1.510697e+04 | 1.494309 | 0.007542 | 0.234303 | 3.409430 | 7.656873 | 1788.390691 | 291.509045 | 1971.005136 | 84.402258 | 98077.939805 | 47.560053 | -122.213896 | 1986.552492 | 12768.455652 |
| std | 2.876566e+09 | 3.671272e+05 | 0.930062 | 0.770163 | 918.440897 | 4.142051e+04 | 0.539989 | 0.086517 | 0.766318 | 0.650743 | 1.175459 | 828.090978 | 442.575043 | 29.373411 | 401.679240 | 53.505026 | 0.138564 | 0.140828 | 685.391304 | 27304.179631 |
| min | 1.000102e+06 | 7.500000e+04 | 0.000000 | 0.000000 | 290.000000 | 5.200000e+02 | 1.000000 | 0.000000 | 0.000000 | 1.000000 | 1.000000 | 290.000000 | 0.000000 | 1900.000000 | 0.000000 | 98001.000000 | 47.155900 | -122.519000 | 399.000000 | 651.000000 |
| 25% | 2.123049e+09 | 3.219500e+05 | 3.000000 | 1.750000 | 1427.000000 | 5.040000e+03 | 1.000000 | 0.000000 | 0.000000 | 3.000000 | 7.000000 | 1190.000000 | 0.000000 | 1951.000000 | 0.000000 | 98033.000000 | 47.471000 | -122.328000 | 1490.000000 | 5100.000000 |
| 50% | 3.904930e+09 | 4.500000e+05 | 3.000000 | 2.250000 | 1910.000000 | 7.618000e+03 | 1.500000 | 0.000000 | 0.000000 | 3.000000 | 7.000000 | 1560.000000 | 0.000000 | 1975.000000 | 0.000000 | 98065.000000 | 47.571800 | -122.230000 | 1840.000000 | 7620.000000 |
| 75% | 7.308900e+09 | 6.450000e+05 | 4.000000 | 2.500000 | 2550.000000 | 1.068800e+04 | 2.000000 | 0.000000 | 0.000000 | 4.000000 | 8.000000 | 2210.000000 | 560.000000 | 1997.000000 | 0.000000 | 98118.000000 | 47.678000 | -122.125000 | 2360.000000 | 10083.000000 |
| max | 9.900000e+09 | 7.700000e+06 | 33.000000 | 8.000000 | 13540.000000 | 1.651359e+06 | 3.500000 | 1.000000 | 4.000000 | 5.000000 | 13.000000 | 9410.000000 | 4820.000000 | 2015.000000 | 2015.000000 | 98199.000000 | 47.777600 | -121.315000 | 6210.000000 | 871200.000000 |
profile = pandas_profiling.ProfileReport(df)
profile.to_file(output_file="../reports/html/pandas_profiling_report.html")
def show_method_attributes(method, ncols=2):
""" Show all the attributes of a given method.
Example:
========
show_method_attributes(list)
"""
x = [I for I in dir(method) if I[0].islower()]
x = [I for I in x if I not in 'os np pd sys time psycopg2'.split()]
return pd.DataFrame(np.array_split(x,ncols)).T.fillna('')
show_method_attributes(profile)
profile.get_unique_file_name()
profile.get_description() # gives description of only one column
# !open ../reports/html/pandas_profiling_report.html
profile2 = pandas_profiling.ProfileReport(pd.DataFrame(df[['sqft_living','price']]))
profile2
profile2.get_description()['table']
pd.DataFrame(profile2.get_description()['table'],index=['sqft_living'])
df[['sqft_living','price']].corr().style.background_gradient()
sns.heatmap(df['sqft_living price'.split()].corr(), annot=True)