From 95ef9371057bca80062a00a1fbde7f515856b92c Mon Sep 17 00:00:00 2001
From: shawk masboob <masboob.shawk@gmail.com>
Date: Fri, 24 Apr 2020 02:34:06 -0400
Subject: [PATCH] linted function file
---
Topological_ML/tda_function.py | 110 ++++++++++++++++++++++-----------
1 file changed, 74 insertions(+), 36 deletions(-)
diff --git a/Topological_ML/tda_function.py b/Topological_ML/tda_function.py
index a2e986d..43db154 100644
--- a/Topological_ML/tda_function.py
+++ b/Topological_ML/tda_function.py
@@ -1,54 +1,92 @@
"""
This file contains all of the functions used within the notebooks.
-Date:
-Author:
+Date: April 24, 2020
+Author: Shawk Masboob
+
+The function `uniform_sampling` was borrowed from Luis Polancocontreras,
+a PhD candidate in the CMSE program at Michigan State University.
+It was slightly tweaked to fit this project.
"""
-import sklearn
-from sklearn.linear_model import LinearRegression
+from sklearn import ensemble
import kmapper as km
-import pandas as pd
import numpy as np
+import pandas as pd
def numpy_to_pandas(sklearn_data):
- """
- Converts scikit-learn numpy data into pandas dataframe.
- Input: name of dataframe
- Output: pandas dataframe
+ """Converts scikit-learn numpy data into pandas dataframe
+
+ Args:
+ sklearn_data (array): name of dataframe
+
+ Returns:
+ panda.array: pandas dataframe
+
"""
data = pd.DataFrame(data=sklearn_data.data, columns=sklearn_data.feature_names)
data['target'] = pd.Series(sklearn_data.target)
return data
-def linear_regression(feature, predictor):
- """
- Ordinary least squares Linear Regression.
- input: x = independent variables
- y = dependent variable
- output: R^2
- """
- model = LinearRegression()
- model.fit(feature, predictor)
- return model.score(feature, predictor)
+def lens_1d(x_array, proj='l2norm', random_num=1729, verbosity=0):
+ """Creates a L^2-Norm for features. This lens highlights expected features in the data.
+
+ Args:
+ X (array): features of dataset
+ proj (string): projection type
+ random_num: random state
+ verbosity: verbosity
+
+ Returns:
+ lens: Isolation Forest, L^2-Norm
+ mapper:
-def lens_1d(features, random_num, verbosity):
- """
- input:
- output:
"""
- model = sklearn.ensemble.IsolationForest(random_state=random_num)
- model.fit(features)
- lens1 = model.decision_function(features).reshape((features.shape[0], 1))
+ if not type(x_array) == np.ndarray:
+ print("your input is not an array")
+ return None, None
+ if type(x_array) == np.ndarray and len(x_array.shape) != 2:
+ print('your input needs to be a 2d array')
+ return None, None
+ proj_type = ['sum', 'mean', 'median', 'max', 'min', 'std', 'dist_mean',
+ 'l2norm', 'knn_distance_n']
+ if proj not in proj_type:
+ print("you may only use the following projections:", proj_type)
+ return None, None
+ # Create a custom 1-D lens with Isolation Forest
+ model = ensemble.IsolationForest(random_state=random_num)
+ model.fit(x_array)
+ lens1 = model.decision_function(x_array).reshape((x_array.shape[0], 1))
+ # Create another 1-D lens with L2-norm
mapper = km.KeplerMapper(verbose=verbosity)
- lens2 = mapper.fit_transform(features, projection="l2norm")
+ lens2 = mapper.fit_transform(x_array, projection=proj)
+ # Combine lenses pairwise to get a 2-D lens i.e. [Isolation Forest, L^2-Norm] lens
lens = np.c_[lens1, lens2]
- return lens
+ return lens, mapper
+
+def uniform_sampling(dist_matrix, n_sample):
+ """Given a distance matrix retunrs an subsamplig that preserves the distribution
+ of the original data set and the covering radious corresponding to
+ the subsampled set.
+
+ Args:
+ dist_matrix (array): Distance matrix
+ n_sample (int): Size of subsample set
+
+ Returns:
+ list_subsample (array): List of indices corresponding to the subsample set.
+ np.max(dist_to_l): Covering radious for the subsample set.
-def county_crosstab(data, county, year, index, columns):
- """
- input:
- output:
"""
- subset_df = data[data.year == year]
- sub_df = subset_df[subset_df.county == county]
- crosstab = pd.crosstab(index=sub_df[index], columns=sub_df[columns])
- return crosstab
+ if not type(dist_matrix) == np.ndarray:
+ print("your input is not an array")
+ return None, None
+ if type(dist_matrix) == np.ndarray and len(dist_matrix.shape) != 2:
+ print('your input needs to be a 2d array')
+ return None, None
+ n_subsample = int(n_sample)
+ if n_subsample <= 0:
+ print("Sampling size should be a positive integer.")
+ return None, None
+ num_points = dist_matrix.shape[0]
+ list_subsample = np.random.choice(num_points, n_subsample)
+ dist_to_l = np.min(dist_matrix[list_subsample, :], axis=0)
+ return list_subsample, np.max(dist_to_l)
--
GitLab