Pandas——比较两个dataframe之间的区别

 

 

import pandas as pd
import datacompy
#导入datafcompy库 比较两个dataframe之间的区别
#同时也可以比较两个txt之间的区别
df1 = pd.read_csv("1.txt",header=None)
df2 = pd.read_csv("22.txt",header=None)
dd = datacompy.Compare(df1,df2,join_columns=0)
print(dd.report())

结果

DataComPy Comparison
--------------------

DataFrame Summary
-----------------

DataFrame Columns Rows
0 df1 1 2
1 df2 1 6

Column Summary
--------------

Number of columns in common: 1
Number of columns in df1 but not in df2: 0
Number of columns in df2 but not in df1: 0

Row Summary
-----------

Matched on: 0
Any duplicates on match values: No
Absolute Tolerance: 0
Relative Tolerance: 0
Number of rows in common: 2
Number of rows in df1 but not in df2: 0
Number of rows in df2 but not in df1: 4

Number of rows with some compared columns unequal: 0
Number of rows with all compared columns equal: 2

Column Comparison
-----------------

Number of columns compared with some values unequal: 0
Number of columns compared with all values equal: 1
Total number of values which compare unequal: 0

Sample Rows Only in df2 (First 10 Columns)
------------------------------------------

0
3 vasdj
4 顺嘿嘿
5 顺顺
2 afdlkaewlhg

 

 

 

import pandas as pd
import datacompy 
import glob
import os

all_files1 = glob.glob(r"C:\Users\15773\Desktop\test\1\*.txt")
all_files2 = glob.glob(r"C:\Users\15773\Desktop\test\2\*.txt")
for file1 in all_files1:
    file1_basename = os.path.basename(file1)
    for file2 in all_files2:
        file2_basename = os.path.basename(file2)
        if file1_basename == file2_basename:
            df1 = pd.read_csv(file1,header=None)
            df2 = pd.read_csv(file2,header=None)
            dd = datacompy.Compare(df1,df2,join_columns=0)
            report = dd.report()
            print(df1)
            print(df2)
            print(report)
            txt_name = str(file1_basename)+"_result.txt"
            result_txt = open(txt_name,'w')
            result_txt.write(report)
            result_txt.close()
print("process done")

 

 

from io import StringIO
import pandas as pd
import datacompy

data1 = """acct_id,dollar_amt,name,float_fld,date_fld
10000001234,123.45,George Maharis,14530.1555,2017-01-01
10000001235,0.45,Michael Bluth,1,2017-01-01
10000001236,1345,George Bluth,,2017-01-01
10000001237,123456,Bob Loblaw,345.12,2017-01-01
10000001239,1.05,Lucille Bluth,,2017-01-01
"""

data2 = """acct_id,dollar_amt,name,float_fld
10000001234,123.4,George Michael Bluth,14530.155
10000001235,0.45,Michael Bluth,
10000001236,1345,George Bluth,1
10000001237,123456,Robert Loblaw,345.12
10000001238,1.05,Loose Seal Bluth,111
"""

df1 = pd.read_csv(StringIO(data1))
df2 = pd.read_csv(StringIO(data2))

compare = datacompy.Compare(
    df1,
    df2,
    join_columns='acct_id',  #You can also specify a list of columns
    abs_tol=0, #Optional, defaults to 0
    rel_tol=0, #Optional, defaults to 0
    df1_name='Original', #Optional, defaults to 'df1'
    df2_name='New' #Optional, defaults to 'df2'
    )
compare.matches(ignore_extra_columns=False)
# False

# This method prints out a human-readable report summarizing and sampling differences
print(compare.report())

DataComPy Comparison
--------------------

DataFrame Summary
-----------------

DataFrame Columns Rows
0 Original 5 5
1 New 4 5

Column Summary
--------------

Number of columns in common: 4
Number of columns in Original but not in New: 1
Number of columns in New but not in Original: 0

Row Summary
-----------

Matched on: acct_id
Any duplicates on match values: No
Absolute Tolerance: 0
Relative Tolerance: 0
Number of rows in common: 4
Number of rows in Original but not in New: 1
Number of rows in New but not in Original: 1

Number of rows with some compared columns unequal: 4
Number of rows with all compared columns equal: 0

Column Comparison
-----------------

Number of columns compared with some values unequal: 3
Number of columns compared with all values equal: 1
Total number of values which compare unequal: 6

Columns with Unequal Values or Types
------------------------------------

Column Original dtype New dtype # Unequal Max Diff # Null Diff
2 dollar_amt float64 float64 1 0.0500 0
0 float_fld float64 float64 3 0.0005 2
1 name object object 2 0.0000 0

Sample Rows with Unequal Values
-------------------------------

acct_id float_fld (Original) float_fld (New)
2 10000001236 NaN 1.000
0 10000001234 14530.1555 14530.155
1 10000001235 1.0000 NaN

acct_id name (Original) name (New)
3 10000001237 Bob Loblaw Robert Loblaw
0 10000001234 George Maharis George Michael Bluth

acct_id dollar_amt (Original) dollar_amt (New)
0 10000001234 123.45 123.4

Sample Rows Only in Original (First 10 Columns)
-----------------------------------------------

acct_id dollar_amt name float_fld date_fld
4 10000001239 1.05 Lucille Bluth NaN 2017-01-01

Sample Rows Only in New (First 10 Columns)
------------------------------------------

acct_id dollar_amt name float_fld
5 10000001238 1.05 Loose Seal Bluth 111.0