Last active
January 25, 2021 12:36
-
-
Save brpy/2939479e81b79c601525940a4afe65e4 to your computer and use it in GitHub Desktop.
Code for Response coding for binary/multi classification tasks using Python.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| import pandas as pd | |
| # Column names of categorical features | |
| categorical_features = ( | |
| "school_state", | |
| "teacher_prefix", | |
| "project_grade_category", | |
| "clean_categories", | |
| "clean_subcategories", | |
| ) | |
| # Name of target variable column | |
| target = "project_is_approved" | |
| response_coding = {} | |
| classes = sorted([0, 1]) | |
| for category in categorical_features: | |
| cat = {} | |
| for sub_category in pd.unique(X_train[category]): | |
| count_dict = pd.value_counts( | |
| X_train[X_train[category] == sub_category][target] | |
| ).to_dict() | |
| count = [count_dict.get(cls, 0) for cls in classes] | |
| prob = tuple(map(lambda ele: ele / sum(count), count)) | |
| cat.update({sub_category: prob}) | |
| response_coding.update({category: cat}) | |
| def get_response_coding(df: pd.DataFrame) -> np.array: | |
| """ | |
| Returns response of type np.array of size (rows, no. of categorical features * n_classes) | |
| """ | |
| n_classes = len(classes) | |
| n_rows = df.shape[0] | |
| n_cols = len(categorical_features) * n_classes | |
| default = tuple([1 / n_classes] * n_classes) | |
| response = np.zeros((n_rows, n_cols), dtype=float) | |
| for category in categorical_features: | |
| start = categorical_features.index(category) * n_classes | |
| cols = (start, start + n_classes) | |
| for sub_category in pd.unique(X_train[category]): | |
| rows = (df[category] == sub_category).values | |
| response[rows, cols[0] : cols[1]] = list( | |
| response_coding[category].get(sub_category, default) | |
| ) | |
| return response | |
| train_response = get_response_coding(X_train) | |
| test_response = get_response_coding(X_test) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Change
categorical_featuresandtargetvariables to fit your dataset.train and test dataframes are named as
X_trainandX_testrespectively.