Merge pull request #1 from kishorek/develop

updated version, documentation & some fixes
kishorek · Jun 22, 2020 · 7247bb1 · 7247bb1
2 parents 657fed8 + 8d11695
commit 7247bb1
Show file tree

Hide file tree

Showing 5 changed files with 138 additions and 15 deletions.
diff --git a/README.md b/README.md
@@ -46,6 +46,139 @@ optional arguments:
   -s, --save-output     Save output to file
 ```
 
+## Examples
+
+### Scenario 1: Simple direct comparison
+
+|id |first   |last    |age|
+|---|--------|--------|---|
+|432|Roy     |Aguilar |46 |
+|914|Janie   |Bowman  |24 |
+|021|Grace   |Copeland|53 |
+|708|Louise  |Franklin|25 |
+|850|Gertrude|Carr    |60 |
+
+vs
+
+|id |first   |last    |age|
+|---|--------|--------|---|
+|432|Roy     |Aguilar |46 |
+|914|Janie   |Bowman  |24 |
+|021|Grace   |Copeland|53 |
+|708|Louise  |Franklin|25 |
+|850|Gertrude|Carr    |60 |
+
+```console
+comparesv file1 file2
+```
+
+Will provide:
+
+|S.No|id      |first   |last|age |
+|----|--------|--------|----|----|
+|1   |True    |True    |True|True|
+|2   |True    |True    |True|True|
+|3   |True    |True    |True|True|
+|4   |True    |True    |True|True|
+|5   |True    |True    |True|True|
+
+and
+
+|S.No|id      |first   |last|age |
+|----|--------|--------|----|----|
+|1   |[432]:[432]|[Roy]:[Roy]|[Aguilar]:[Aguilar]|[46]:[46]|
+|2   |[914]:[914]|[Janie]:[Janie]|[Bowman]:[Bowman]|[24]:[24]|
+|3   |[021]:[021]|[Grace]:[Grace]|[Copeland]:[Copeland]|[53]:[53]|
+|4   |[708]:[708]|[Louise]:[Louise]|[Franklin]:[Franklin]|[25]:[25]|
+|5   |[850]:[850]|[Gertrude]:[Gertrude]|[Carr]:[Carr]|[60]:[60]|
+
+---
+### Scenario 2: Fuzzy column names
+
+|id |first   |last    |age of student|
+|---|--------|--------|--------------|
+|432|Roy     |Aguilar |46            |
+|914|Janie   |Bowman  |24            |
+
+and 
+
+|id |first   |last    |age|
+|---|--------|--------|---|
+|432|Roy     |Aguilar |46 |
+|914|Janie   |Bowman  |24 |
+
+```console
+comparesv file1.csv file2.csv --column-match 'fuzzy'
+```
+
+will provide
+|S.No|id      |first   |last|age |
+|----|--------|--------|----|----|
+|1   |True    |True    |True|True|
+|2   |True    |True    |True|True|
+---
+### Scenario 3: Fuzzy row order - Differnt ordered textual data
+
+|id |first   |last    |age|
+|---|--------|--------|---|
+|432|Roy     |Aguilar |46 |
+|914|Janie   |Bowman  |24 |
+|021|Grace   |Copeland|53 |
+
+and
+
+|id |first   |last    |age of student|
+|---|--------|--------|--------------|
+|021|Grace   |Copeland|53            |
+|432|Roy     |Aguilar |46            |
+|914|Janie   |Bowman  |24            |
+
+```console
+comparesv file1.csv file2.csv --column-match 'fuzzy' --row-match 'fuzzy'
+```
+will provide
+
+|S.No|id      |first   |last|age |
+|----|--------|--------|----|----|
+|1   |True    |True    |True|True|
+|2   |True    |True    |True|True|
+|3   |True    |True    |True|True|
+--- 
+### Scenario 3: Deep row order - Different ordered numerical data
+
+|year1|year2   |year3   |year|
+|-----|--------|--------|----|
+|751  |609     |590     |930 |
+|417  |501     |441     |763 |
+|691  |621     |941     |563 |
+|179  |781     |335     |225 |
+|961  |530     |433     |571 |
+
+and
+
+|year1|year2   |year3   |year|
+|-----|--------|--------|----|
+|961  |530     |433     |571 |
+|751  |609     |590     |930 |
+|691  |621     |941     |563 |
+|179  |781     |335     |225 |
+|417  |501     |441     |763 |
+
+```console
+comparesv file1.csv file2.csv --row-match 'deep'
+```
+
+|S.No|year1   |year2   |year3|year|
+|----|--------|--------|-----|----|
+|1   |True    |True    |True |True|
+|2   |True    |True    |True |True|
+|3   |True    |True    |True |True|
+|4   |True    |True    |True |True|
+|5   |True    |True    |True |True|
+
+---
+### Scenario n: Unlimited options. Please explore the options below
+---
 ## Description
 
 The first file is considered as the source file. It will be compared against the second file. Refer the below options to finetune the way it works.

diff --git a/cli.py b/cli.py
@@ -21,7 +21,6 @@ def main():
     sys.stderr.write('Starting up...\n')
     try:
         file1, file2, args = arguments()
-        print(args)
         data1, headers1 = read(*file1)
         data2, headers2 = read(*file2)
         results = comparesv.run(data1, headers1, data2, headers2, ticker=ticker, **args)
@@ -113,5 +112,4 @@ def format(results, keys):
 
 
 if __name__ == '__main__':
-    main()
-
+    main()
diff --git a/comparesv.py b/comparesv.py
@@ -292,13 +292,4 @@ def predict_column_type(data):
     elif int in data_types:
         return "int"
     else:
-        return "str"
-
-h1 = ["id", "age"]
-h2 = ["id", "age","gender"]
-d1 = [["A1", 23], ["A2", 24], ["A3", 34]]
-d2 = [["A1", 23,"M"], ["A2", 24,"F"], ["A3", 34,"O"]]
-
-output = run(d1, h1, d2, h2, include_addnl_columns='fuzzy')
-from pprint import pprint
-pprint(output)
+        return "str"
diff --git a/setup.py b/setup.py
@@ -28,7 +28,8 @@ def open_file(fname):
 		'tqdm==4.18.0',
 		'unidecode==1.1.1',
 		'doublemetaphone==0.1',
-		'fuzzywuzzy==0.18.0'
+		'fuzzywuzzy==0.18.0',
+		'python-Levenshtein==0.12.0'
 	],
 	entry_points={
 		'console_scripts': [

diff --git a/version.py b/version.py
@@ -1 +1 @@
-__version__ = 0.11
+__version__ = 0.12