AutomatedCleaning 1.2__tar.gz → 1.3__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- automatedcleaning-1.3/AutomatedCleaning.egg-info/PKG-INFO +66 -0
- {automatedcleaning-1.2 → automatedcleaning-1.3}/AutomatedCleaning.egg-info/SOURCES.txt +2 -2
- automatedcleaning-1.3/AutomatedCleaning.egg-info/requires.txt +26 -0
- automatedcleaning-1.3/PKG-INFO +66 -0
- automatedcleaning-1.3/automatedcleaning/__init__.py +3 -0
- {automatedcleaning-1.2 → automatedcleaning-1.3}/automatedcleaning/cleaning.py +1484 -1269
- automatedcleaning-1.3/pyproject.toml +53 -0
- automatedcleaning-1.3/tests/test_cleaning.py +142 -0
- automatedcleaning-1.2/AutomatedCleaning.egg-info/PKG-INFO +0 -173
- automatedcleaning-1.2/AutomatedCleaning.egg-info/requires.txt +0 -119
- automatedcleaning-1.2/PKG-INFO +0 -173
- automatedcleaning-1.2/automatedcleaning/__init__.py +0 -1
- automatedcleaning-1.2/automatedcleaning/cleaning_update.py +0 -1273
- automatedcleaning-1.2/setup.py +0 -144
- {automatedcleaning-1.2 → automatedcleaning-1.3}/AutomatedCleaning.egg-info/dependency_links.txt +0 -0
- {automatedcleaning-1.2 → automatedcleaning-1.3}/AutomatedCleaning.egg-info/top_level.txt +0 -0
- {automatedcleaning-1.2 → automatedcleaning-1.3}/README.md +0 -0
- {automatedcleaning-1.2 → automatedcleaning-1.3}/setup.cfg +0 -0
|
@@ -0,0 +1,66 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: AutomatedCleaning
|
|
3
|
+
Version: 1.3
|
|
4
|
+
Summary: Automated Data Cleaning Library
|
|
5
|
+
Author-email: Abhishek Kumar Singh <dataspoof007@gmail.com>
|
|
6
|
+
License-Expression: MIT
|
|
7
|
+
Project-URL: Homepage, https://github.com/DataSpoof/AutomatedCleaning
|
|
8
|
+
Classifier: Programming Language :: Python :: 3
|
|
9
|
+
Classifier: Operating System :: OS Independent
|
|
10
|
+
Requires-Python: >=3.11
|
|
11
|
+
Description-Content-Type: text/markdown
|
|
12
|
+
Requires-Dist: numpy
|
|
13
|
+
Requires-Dist: pandas
|
|
14
|
+
Requires-Dist: polars
|
|
15
|
+
Requires-Dist: nltk
|
|
16
|
+
Requires-Dist: matplotlib
|
|
17
|
+
Requires-Dist: missingno
|
|
18
|
+
Requires-Dist: plotly
|
|
19
|
+
Requires-Dist: scikit-learn
|
|
20
|
+
Requires-Dist: pyfiglet
|
|
21
|
+
Provides-Extra: llm
|
|
22
|
+
Requires-Dist: langchain-anthropic; extra == "llm"
|
|
23
|
+
Provides-Extra: pii
|
|
24
|
+
Requires-Dist: presidio-analyzer; extra == "pii"
|
|
25
|
+
Requires-Dist: presidio-anonymizer; extra == "pii"
|
|
26
|
+
Provides-Extra: all
|
|
27
|
+
Requires-Dist: langchain-anthropic; extra == "all"
|
|
28
|
+
Requires-Dist: presidio-analyzer; extra == "all"
|
|
29
|
+
Requires-Dist: presidio-anonymizer; extra == "all"
|
|
30
|
+
Provides-Extra: dev
|
|
31
|
+
Requires-Dist: pytest; extra == "dev"
|
|
32
|
+
Requires-Dist: build; extra == "dev"
|
|
33
|
+
Requires-Dist: twine; extra == "dev"
|
|
34
|
+
|
|
35
|
+
# AutomatedCleaning
|
|
36
|
+
|
|
37
|
+
AutomatedCleaning is a Python library for automated data cleaning.It helps preprocess and analyze datasets by handling missing values, outliers, spelling corrections, and more.
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
## Features
|
|
42
|
+
- Supports both large (100+ GB) and small datasets
|
|
43
|
+
- Detects and handles missing values and duplicate records
|
|
44
|
+
- Identifies and corrects spelling errors in categorical values
|
|
45
|
+
- Detect outliers
|
|
46
|
+
- Detects and fixes data imbalance
|
|
47
|
+
- Identifies and corrects skewness in numerical data
|
|
48
|
+
- Checks for correlation and detects multicollinearity
|
|
49
|
+
- Analyzes cardinality in categorical columns
|
|
50
|
+
- Identifies and cleans text columns
|
|
51
|
+
- Detect JSON-type columns
|
|
52
|
+
- Detect and mask PII types of columns
|
|
53
|
+
- Performs univariate, bivariate, and multivariate analysis
|
|
54
|
+
|
|
55
|
+
|
|
56
|
+
## Installation
|
|
57
|
+
```bash
|
|
58
|
+
pip install AutomatedCleaning
|
|
59
|
+
```
|
|
60
|
+
|
|
61
|
+
## Usage
|
|
62
|
+
```bash
|
|
63
|
+
import automatedcleaning as ac
|
|
64
|
+
df = ac.load_data("dataset.csv")
|
|
65
|
+
df_cleaned = ac.clean_data(df)
|
|
66
|
+
```
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
README.md
|
|
2
|
-
|
|
2
|
+
pyproject.toml
|
|
3
3
|
AutomatedCleaning.egg-info/PKG-INFO
|
|
4
4
|
AutomatedCleaning.egg-info/SOURCES.txt
|
|
5
5
|
AutomatedCleaning.egg-info/dependency_links.txt
|
|
@@ -7,4 +7,4 @@ AutomatedCleaning.egg-info/requires.txt
|
|
|
7
7
|
AutomatedCleaning.egg-info/top_level.txt
|
|
8
8
|
automatedcleaning/__init__.py
|
|
9
9
|
automatedcleaning/cleaning.py
|
|
10
|
-
|
|
10
|
+
tests/test_cleaning.py
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
numpy
|
|
2
|
+
pandas
|
|
3
|
+
polars
|
|
4
|
+
nltk
|
|
5
|
+
matplotlib
|
|
6
|
+
missingno
|
|
7
|
+
plotly
|
|
8
|
+
scikit-learn
|
|
9
|
+
pyfiglet
|
|
10
|
+
|
|
11
|
+
[all]
|
|
12
|
+
langchain-anthropic
|
|
13
|
+
presidio-analyzer
|
|
14
|
+
presidio-anonymizer
|
|
15
|
+
|
|
16
|
+
[dev]
|
|
17
|
+
pytest
|
|
18
|
+
build
|
|
19
|
+
twine
|
|
20
|
+
|
|
21
|
+
[llm]
|
|
22
|
+
langchain-anthropic
|
|
23
|
+
|
|
24
|
+
[pii]
|
|
25
|
+
presidio-analyzer
|
|
26
|
+
presidio-anonymizer
|
|
@@ -0,0 +1,66 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: AutomatedCleaning
|
|
3
|
+
Version: 1.3
|
|
4
|
+
Summary: Automated Data Cleaning Library
|
|
5
|
+
Author-email: Abhishek Kumar Singh <dataspoof007@gmail.com>
|
|
6
|
+
License-Expression: MIT
|
|
7
|
+
Project-URL: Homepage, https://github.com/DataSpoof/AutomatedCleaning
|
|
8
|
+
Classifier: Programming Language :: Python :: 3
|
|
9
|
+
Classifier: Operating System :: OS Independent
|
|
10
|
+
Requires-Python: >=3.11
|
|
11
|
+
Description-Content-Type: text/markdown
|
|
12
|
+
Requires-Dist: numpy
|
|
13
|
+
Requires-Dist: pandas
|
|
14
|
+
Requires-Dist: polars
|
|
15
|
+
Requires-Dist: nltk
|
|
16
|
+
Requires-Dist: matplotlib
|
|
17
|
+
Requires-Dist: missingno
|
|
18
|
+
Requires-Dist: plotly
|
|
19
|
+
Requires-Dist: scikit-learn
|
|
20
|
+
Requires-Dist: pyfiglet
|
|
21
|
+
Provides-Extra: llm
|
|
22
|
+
Requires-Dist: langchain-anthropic; extra == "llm"
|
|
23
|
+
Provides-Extra: pii
|
|
24
|
+
Requires-Dist: presidio-analyzer; extra == "pii"
|
|
25
|
+
Requires-Dist: presidio-anonymizer; extra == "pii"
|
|
26
|
+
Provides-Extra: all
|
|
27
|
+
Requires-Dist: langchain-anthropic; extra == "all"
|
|
28
|
+
Requires-Dist: presidio-analyzer; extra == "all"
|
|
29
|
+
Requires-Dist: presidio-anonymizer; extra == "all"
|
|
30
|
+
Provides-Extra: dev
|
|
31
|
+
Requires-Dist: pytest; extra == "dev"
|
|
32
|
+
Requires-Dist: build; extra == "dev"
|
|
33
|
+
Requires-Dist: twine; extra == "dev"
|
|
34
|
+
|
|
35
|
+
# AutomatedCleaning
|
|
36
|
+
|
|
37
|
+
AutomatedCleaning is a Python library for automated data cleaning.It helps preprocess and analyze datasets by handling missing values, outliers, spelling corrections, and more.
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
## Features
|
|
42
|
+
- Supports both large (100+ GB) and small datasets
|
|
43
|
+
- Detects and handles missing values and duplicate records
|
|
44
|
+
- Identifies and corrects spelling errors in categorical values
|
|
45
|
+
- Detect outliers
|
|
46
|
+
- Detects and fixes data imbalance
|
|
47
|
+
- Identifies and corrects skewness in numerical data
|
|
48
|
+
- Checks for correlation and detects multicollinearity
|
|
49
|
+
- Analyzes cardinality in categorical columns
|
|
50
|
+
- Identifies and cleans text columns
|
|
51
|
+
- Detect JSON-type columns
|
|
52
|
+
- Detect and mask PII types of columns
|
|
53
|
+
- Performs univariate, bivariate, and multivariate analysis
|
|
54
|
+
|
|
55
|
+
|
|
56
|
+
## Installation
|
|
57
|
+
```bash
|
|
58
|
+
pip install AutomatedCleaning
|
|
59
|
+
```
|
|
60
|
+
|
|
61
|
+
## Usage
|
|
62
|
+
```bash
|
|
63
|
+
import automatedcleaning as ac
|
|
64
|
+
df = ac.load_data("dataset.csv")
|
|
65
|
+
df_cleaned = ac.clean_data(df)
|
|
66
|
+
```
|