Kaggle酒推荐，winemag-data-130k-v2.csv

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
from scipy.stats import kurtosis,skew
from scipy import stats

函数定义

def resumetable(df):
    print(f"Dataset Shape: {df.shape}")
    summary = pd.DataFrame(df.dtypes,columns=['dtypes'])
    summary = summary.reset_index()
    summary['Name'] = summary['index']
    summary = summary[['Name','dtypes']]
    summary['Missing'] = df.isnull().sum().values    
    summary['Uniques'] = df.nunique().values
    summary['First Value'] = df.loc[0].values
    summary['Second Value'] = df.loc[1].values
    summary['Third Value'] = df.loc[2].values

    for name in summary['Name'].value_counts().index:
        summary.loc[summary['Name'] == name, 'Entropy'] = round(stats.entropy(df[name].value_counts(normalize=True), base=2),2) 

    return summary

def CalcOutliers(df_num): 
    '''
    
    Leonardo Ferreira 20/10/2018
    Set a numerical value and it will calculate the upper, lower and total number of outliers
    It will print a lot of statistics of the numerical feature that you set on input
    
    '''
    # calculating mean and std of the array
    data_mean, data_std = np.mean(df_num), np.std(df_num)

    # seting the cut line to both higher and lower values
    # You can change this value
    cut = data_std * 3

    #Calculating the higher and lower cut values
    lower, upper = data_mean - cut, data_mean + cut

    # creating an array of lower, higher and total outlier values 
    outliers_lower = [x for x in df_num if x < lower]
    outliers_higher = [x for x in df_num if x > upper]
    outliers_total = [x for x in df_num if x < lower or x > upper]

    # array without outlier values
    outliers_removed = [x for x in df_num if x > lower and x < upper]
    
    print('Identified lowest outliers: %d' % len(outliers_lower)) # printing total number of values in lower cut of outliers
    print('Identified upper outliers: %d' % len(outliers_higher)) # printing total number of values in higher cut of outliers
    print('Identified outliers: %d' % len(outliers_total)) # printing total number of values outliers of both sides
    print('Non-outlier observations: %d' % len(outliers_removed)) # printing total number of non outlier values
    print("Total percentual of Outliers: ", round((len(outliers_total) / len(outliers_removed) )*100, 4)) # Percentual of outliers in points
    
    return

标签：lower,csv,df,Kaggle,summary,v2,values,total,outliers
来源： https://blog.csdn.net/sinat_37574187/article/details/120219162