python-数据统计

import sys

import pandas as pd

import numpy as np

import matplotlib

import matplotlib.pyplot as plt

import random as rd

 

print('Python: {}'.format(sys.version))

print('pandas: {}'.format(pd.__version__))

print('numpy: {}'.format(np.__version__))

print('matplotlib {}'.format(matplotlib.__version__))

 

df = pd.read_csv('Sacramentorealestatetransactions.csv')

 

print(df.head(10))

 

print(df.describe())

 

df_NumData = df[['beds','baths','sq__ft','price']]

print(df_NumData.describe())

 

df['price'].hist(bins=100)

plt.show()

 

df.boxplot(column='price')

plt.show()

 

df.boxplot(column='price', by = 'beds')

plt.show()

 

df[['price','beds']].groupby('beds').boxplot()

plt.show()

 

bedcount = df['beds'].value_counts()

print(bedcount)

 

bedcount = df['beds'].value_counts(ascending=True)

print(bedcount)

 

print(bedcount.sort_index(axis=0,ascending=True))

 

print(bedcount.sort_index(axis=0,ascending=False))

 

print(bedcount.sort_values(axis=0))

 

avgPricePivot = df.pivot_table(values='price',index=['beds'],aggfunc=lambda x: x.mean())

print(avgPricePivot)

 

avgPricePivot = df.pivot_table(values='price',index=['beds'],aggfunc=lambda x: [x.mean(),x.min(), x.max()])

print(avgPricePivot)

 

pd.plotting.scatter_matrix(df_NumData)

plt.show()