clustering-imputation 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

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.
@@ -0,0 +1,113 @@
1
+ Metadata-Version: 2.1
2
+ Name: clustering-imputation
3
+ Version: 1.0.1
4
+ Summary: Adding correlation to handle MNAR
5
+ Author: MRINAL KANGSA BANIK
6
+ Author-email: <manukbanik30@gmail.com>
7
+ Keywords: python,imputation,MNAR
8
+ Classifier: Development Status :: 1 - Planning
9
+ Classifier: Intended Audience :: Developers
10
+ Classifier: Programming Language :: Python :: 3
11
+ Classifier: Operating System :: Unix
12
+ Classifier: Operating System :: MacOS :: MacOS X
13
+ Classifier: Operating System :: Microsoft :: Windows
14
+ Description-Content-Type: text/markdown
15
+ License-File: LICENSE
16
+ Requires-Dist: numpy
17
+ Requires-Dist: pandas
18
+ Requires-Dist: sklearn
19
+ Requires-Dist: fancyimpute
20
+
21
+
22
+ # Clustering Imputation
23
+
24
+ ## Installation
25
+
26
+ To install the package, run:
27
+
28
+ ```bash
29
+
30
+ pip install clustering-imputation==1.0.0
31
+
32
+ ```
33
+
34
+ ## Usage
35
+
36
+
37
+
38
+ ```python
39
+
40
+ from clustering_imputation import clusterImputer
41
+
42
+ df = ... # Load your dataset
43
+
44
+ x = clusterImputer(df, "mice", "mean", 0.4, 10)
45
+
46
+ x.impute()
47
+
48
+ ```
49
+
50
+ # About the Package
51
+
52
+
53
+
54
+ ## Problem Statement
55
+
56
+
57
+
58
+ * Traditional imputation techniques face several challenges:
59
+
60
+
61
+
62
+ * High-Dimensional and Sparse Data: Existing methods struggle with large, sparse datasets; efficient techniques for such cases are needed.
63
+
64
+
65
+
66
+ * Temporal Dependencies: Current methods often overlook temporal correlations in data.
67
+
68
+ ## Need to develop a new algo
69
+
70
+ * Non-Random Missingness: Few methods address non-random missing patterns; improvements here could boost real-world application accuracy. We aim to develop an imputation method that considers "Missing Not at Random" (MNAR).
71
+
72
+
73
+
74
+ * Computational Complexity: MICE and EM methods are computationally expensive for high-dimensional data. Our approach aims to reduce time complexity.
75
+
76
+
77
+
78
+ ## Philosophy of Our Solution: Clustered MICE/EM
79
+
80
+
81
+
82
+ We propose a clustering-based approach:
83
+
84
+
85
+
86
+ * Identify correlations between features.
87
+
88
+
89
+
90
+ * Apply MICE/EM within clusters rather than on the entire dataset.
91
+
92
+
93
+
94
+ * Combine results to reconstruct the dataset.
95
+
96
+
97
+
98
+ * This method effectively handles MNAR data by leveraging feature correlations.
99
+
100
+ For further details refer this [ppt](https://docs.google.com/presentation/d/1UZ2uDkleSgB2ZttjG1D6nmQhqk7uz5FQRW5UmSkB0Sg/edit?usp=sharing)
101
+
102
+ ## Contributing
103
+
104
+
105
+
106
+ Pull requests are welcome. For major changes, please open an issue first
107
+
108
+ to discuss what you would like to change.
109
+
110
+
111
+
112
+ Please make sure to update tests as appropriate.
113
+
@@ -10,8 +10,8 @@ clustering_imputation/clusterBase/clustering.py,sha256=vs_btfkRL0wdeVbJqIMJduZvp
10
10
  clustering_imputation/clusterBase/ohe.py,sha256=3KRnDpTNerWYY51m915gMx-UG1GrB1Q2Zu65VR4pOaY,725
11
11
  clustering_imputation/dummyData/__init__.py,sha256=d3J6YLwGNjEQXSKP33oLxFQVS8kYW4wWpvuZMt5_Pm0,30
12
12
  clustering_imputation/dummyData/dataCreation.py,sha256=N2DBcmtqPirZ1i32har4wb9aUJ_OI6GWTKtFYQfXOlw,653
13
- clustering_imputation-1.0.0.dist-info/LICENSE,sha256=-QiwYzJ5Lmyq5xOcOdvNjJM_r9GB-d2RLyULii-1iJw,1097
14
- clustering_imputation-1.0.0.dist-info/METADATA,sha256=g8KMlkF5bXeEn4re5EcgfyT-OhMxWeOTxBFAI_Lsr6w,694
15
- clustering_imputation-1.0.0.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
16
- clustering_imputation-1.0.0.dist-info/top_level.txt,sha256=i9XDry3xiyewwukLIRRSWbuRRmG0GpkeIXy3-zaYjAY,22
17
- clustering_imputation-1.0.0.dist-info/RECORD,,
13
+ clustering_imputation-1.0.1.dist-info/LICENSE,sha256=-QiwYzJ5Lmyq5xOcOdvNjJM_r9GB-d2RLyULii-1iJw,1097
14
+ clustering_imputation-1.0.1.dist-info/METADATA,sha256=fas3Uq0-Y1o3V3PyhS4un3G0Xd1bLUoCmS0TEeHkRCk,2474
15
+ clustering_imputation-1.0.1.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
16
+ clustering_imputation-1.0.1.dist-info/top_level.txt,sha256=i9XDry3xiyewwukLIRRSWbuRRmG0GpkeIXy3-zaYjAY,22
17
+ clustering_imputation-1.0.1.dist-info/RECORD,,
@@ -1,23 +0,0 @@
1
- Metadata-Version: 2.1
2
- Name: clustering-imputation
3
- Version: 1.0.0
4
- Summary: Adding correlation to handle MNAR
5
- Author: MRINAL KANGSA BANIK
6
- Author-email: <manukbanik30@gmail.com>
7
- Keywords: python,imputation,MNAR
8
- Classifier: Development Status :: 1 - Planning
9
- Classifier: Intended Audience :: Developers
10
- Classifier: Programming Language :: Python :: 3
11
- Classifier: Operating System :: Unix
12
- Classifier: Operating System :: MacOS :: MacOS X
13
- Classifier: Operating System :: Microsoft :: Windows
14
- Description-Content-Type: text/markdown
15
- License-File: LICENSE
16
- Requires-Dist: numpy
17
- Requires-Dist: pandas
18
- Requires-Dist: sklearn
19
- Requires-Dist: fancyimpute
20
-
21
-
22
- Hey we will write it later
23
-