Data Summary

import pandas as pd
import datetime
from data_describe import data_summary
from datetime import datetime

from sklearn.datasets import load_boston
data = load_boston()
df = pd.DataFrame(data.data, columns=list(data.feature_names))
df['target'] = data.target
df.head(1)

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.09	1.0	296.0	15.3	396.9	4.98	24.0

# Change data types to demonstrate data summary
df['AGE'] = df['AGE'].map(lambda x: "young" if x < 29 else "old")
df["AgeFlag"] = df['AGE'].astype(bool)
df['ZN'] = df['ZN'].astype(int)
df['Date'] = datetime.strptime('1/1/2008 1:30 PM', '%m/%d/%Y %I:%M %p')

data_summary(df)

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target	AgeFlag	Date
Data Type	float64	int32	float64	float64	float64	float64	object	float64	float64	float64	float64	float64	float64	float64	bool	datetime64[ns]
Mean	3.61352	11.3478	11.1368	0.06917	0.554695	6.28463		3.79504	9.54941	408.237	18.4555	356.674	12.6531	22.5328	1	2008-01-01 13:30:00
Standard Deviation	8.60155	23.3106	6.86035	0.253994	0.115878	0.702617		2.10571	8.70726	168.537	2.16495	91.2949	7.14106	9.1971	0
Median	0.25651	0	9.69	0	0.538	6.2085		3.20745	5	330	19.05	391.44	11.36	21.2	1
Min	0.00632	0	0.46	0	0.385	3.561		1.1296	1	187	12.6	0.32	1.73	5
Max	88.9762	100	27.74	1	0.871	8.78		12.1265	24	711	22	396.9	37.97	50
# Zeros	0	372	0	471	0	0		0	0	0	0	0	0	0
# Nulls	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
% Most Frequent Value	0.4	73.52	26.09	93.08	4.55	0.59	88.14	0.99	26.09	26.09	27.67	23.91	0.59	3.16	100	100