Created
February 22, 2021 19:49
-
-
Save makispl/94b41da04b85a61b9b6c4bb35c91cebe to your computer and use it in GitHub Desktop.
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
# Switch to a copy of the labeled dataframe | |
df_no_nuls_2 = df_no_nuls.copy() | |
# Randomise the df | |
shuffled_rows = np.random.permutation(df_no_nuls_2.index) | |
df_no_nuls_2 = df_no_nuls_2.loc[shuffled_rows] | |
# Split to train and test datasets | |
train = df_no_nuls_2.iloc[:int(df_no_nuls_2.shape[0]*0.8)].copy() | |
test = df_no_nuls_2.iloc[int(df_no_nuls_2.shape[0]*0.8):].copy().reset_index() | |
# Subset to the numerical columns we are about to use on the ML algorithm | |
train_data = train[['rating', 'alcohol', 'age']].copy() | |
test_data = test[['rating', 'alcohol', 'age']].copy() | |
# List the unique clasters | |
unique_clusters = train['cluster'].unique() | |
unique_clusters.sort() | |
models = {} | |
# Train each binary classification model | |
for cluster in unique_clusters: | |
X = train[['rating', 'alcohol', 'age']].copy() | |
y = train['cluster'] == cluster | |
model = LogisticRegression() | |
model.fit(X, y) | |
models[cluster] = model | |
testing_probs = pd.DataFrame(columns=unique_clusters) | |
# Test the models | |
for cluster in unique_clusters: | |
X_test = test[['rating', 'alcohol', 'age']].copy() | |
testing_probs[cluster] = models[cluster].predict_proba(X_test)[:,1] | |
# Label the new data | |
test['pred_cluster'] = testing_probs.idxmax(axis=1) | |
# Evaluate the model | |
accuracy = (test['cluster'] == test['pred_cluster']).sum() / test.shape[0] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment