From 84ec9414e45380a5e946d4f73b921b274ecd4be7 Mon Sep 17 00:00:00 2001 From: thor-harsh <105957576+thor-harsh@users.noreply.github.com> Date: Wed, 27 Sep 2023 12:01:42 +0530 Subject: [PATCH] Update k_means_clust.py (#8996) * Update k_means_clust.py * Apply suggestions from code review --------- Co-authored-by: Tianyi Zheng --- machine_learning/k_means_clust.py | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/machine_learning/k_means_clust.py b/machine_learning/k_means_clust.py index 7c8142aab..d93c5addf 100644 --- a/machine_learning/k_means_clust.py +++ b/machine_learning/k_means_clust.py @@ -11,10 +11,10 @@ Inputs: - initial_centroids , initial centroid values generated by utility function(mentioned in usage). - maxiter , maximum number of iterations to process. - - heterogeneity , empty list that will be filled with hetrogeneity values if passed + - heterogeneity , empty list that will be filled with heterogeneity values if passed to kmeans func. Usage: - 1. define 'k' value, 'X' features array and 'hetrogeneity' empty list + 1. define 'k' value, 'X' features array and 'heterogeneity' empty list 2. create initial_centroids, initial_centroids = get_initial_centroids( X, @@ -31,8 +31,8 @@ Usage: record_heterogeneity=heterogeneity, verbose=True # whether to print logs in console or not.(default=False) ) - 4. Plot the loss function, hetrogeneity values for every iteration saved in - hetrogeneity list. + 4. Plot the loss function and heterogeneity values for every iteration saved in + heterogeneity list. plot_heterogeneity( heterogeneity, k @@ -198,13 +198,10 @@ def report_generator( df: pd.DataFrame, clustering_variables: np.ndarray, fill_missing_report=None ) -> pd.DataFrame: """ - Function generates easy-erading clustering report. It takes 2 arguments as an input: - DataFrame - dataframe with predicted cluester column; - FillMissingReport - dictionary of rules how we are going to fill missing - values of for final report generate (not included in modeling); - in order to run the function following libraries must be imported: - import pandas as pd - import numpy as np + Generates a clustering report. This function takes 2 arguments as input: + df - dataframe with predicted cluster column + fill_missing_report - dictionary of rules on how we are going to fill in missing + values for final generated report (not included in modelling); >>> data = pd.DataFrame() >>> data['numbers'] = [1, 2, 3] >>> data['col1'] = [0.5, 2.5, 4.5] @@ -306,10 +303,10 @@ def report_generator( a.columns = report.columns # rename columns to match report report = report.drop( report[report.Type == "count"].index - ) # drop count values except cluster size + ) # drop count values except for cluster size report = pd.concat( [report, a, clustersize, clusterproportion], axis=0 - ) # concat report with clustert size and nan values + ) # concat report with cluster size and nan values report["Mark"] = report["Features"].isin(clustering_variables) cols = report.columns.tolist() cols = cols[0:2] + cols[-1:] + cols[2:-1]