python - 在 Python 中，使用 pandasql：查询返回“Empty DataFrame”

Question

在 Python 中，使用 pandasql：查询返回“Empty DataFrame”

import pandas as pd
import sqlite3 as db
import pandasql
    dataSet = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data",header=None)
    type(dataSet)
    dataSet.columns = ['age', 'workclass','fnlwgt','education','education_num','marital_status','occupation','relationship'
                ,'race','sex','capital_gain','capital_loss','hours_per_week','native_country','salary']
    dataSet.head()
    from pandasql import sqldf
    q1 = "select distinct sex from dataSet where sex='Male';"
    pysqldf = lambda q: sqldf(q, globals())
    print(pysqldf(q1))

Answer 1

对于这个数据集，我检查了实际数据并在列中找到了空格。

所以首先我们需要对数据进行清理，然后我们可以对其进行转换。

为了清洁，我们需要修剪空白。为此，我编写trim_all_the_columns了删除所有空格的函数

上述数据集的代码

#!/usr/bin/env python
# coding: utf-8

#import required packages

import pandas as pd
import sqlite3 as db
import pandasql as ps
from pandasql import sqldf 

#give the path location from where data is loaded, in your case give "https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data"

inputpath=r'C:\Users\Z0040B9K\Desktop\SIGShowcase\adult.data.txt'

#Trim whitespace from ends of each value across all series in dataframe

def trim_all_the_columns(df):
    trim_strings = lambda x: x.strip() if type(x) is str else x
    return df.applymap(trim_strings)

#creating dataframe
dataSet = pd.read_csv(inputpath,header=None)

#calling trim function over the dataframe to remove all whitespaces
dataSet = trim_all_the_columns(dataSet)

type(dataSet)

dataSet.columns = ['age', 'workclass','fnlwgt','education','education_num','marital_status','occupation','relationship' ,'race','sex','capital_gain','capital_loss','hours_per_week','native_country','salary']

#sql query
q1 = "select distinct sex from dataSet where sex='Male';"
#this will return distinct result of **Male** column and that will be 0 
# If you add any other column like **age** or something else you will get result

#q1 = "select distinct age,sex from dataSet where sex='Male';"

pysqldf = lambda q: sqldf(q, globals()) 

#print result
print(pysqldf(q1))

#this also can be use to print result 

print(ps.sqldf(q1, locals()))

查找结果输出：for query

q1 = "select distinct age, sex from dataSet where sex='Male';"

查找查询的结果输出

 q1 = "select distinct sex from dataSet where sex='Male';"