From 2b04f97ccaef7ff5c9c228623db1cd7d2d676d48 Mon Sep 17 00:00:00 2001
From: Siddharth Chaini <40721514+sidchaini@users.noreply.github.com>
Date: Mon, 21 Oct 2024 11:43:07 -0400
Subject: [PATCH] lint: Fixed flake8 fail

---
 distclassipy/classifier.py |   4 +-
 distclassipy/robustness.py | 106 ++++++++++++++++++-------------------
 2 files changed, 55 insertions(+), 55 deletions(-)

diff --git a/distclassipy/classifier.py b/distclassipy/classifier.py
index 12a0b40..2aeb7ae 100644
--- a/distclassipy/classifier.py
+++ b/distclassipy/classifier.py
@@ -28,10 +28,10 @@
 import scipy
 
 from sklearn.base import BaseEstimator, ClassifierMixin
-from sklearn.utils.multiclass import unique_labels
-from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
 from sklearn.metrics import accuracy_score
 from sklearn.model_selection import train_test_split
+from sklearn.utils.multiclass import unique_labels
+from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
 
 from .distances import Distance, _ALL_METRICS
 
diff --git a/distclassipy/robustness.py b/distclassipy/robustness.py
index 37dd20b..34261c8 100644
--- a/distclassipy/robustness.py
+++ b/distclassipy/robustness.py
@@ -1,70 +1,70 @@
-from typing import Callable, Tuple
+# from typing import Callable, Tuple
 
-import numpy as np
+# import numpy as np
 
-import pandas as pd
+# import pandas as pd
 
-import scipy
+# import scipy
 
-from sklearn.base import BaseEstimator, ClassifierMixin
-from sklearn.utils.multiclass import unique_labels
-from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score
+# from sklearn.base import BaseEstimator, ClassifierMixin
+# from sklearn.utils.multiclass import unique_labels
+# from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
+# from sklearn.model_selection import train_test_split
+# from sklearn.metrics import accuracy_score
 
-from .distances import Distance, _ALL_METRICS
+# from .distances import Distance, _ALL_METRICS
 
 
-def assemble_best_classifier(
-    clf: BaseEstimator,
-    X: np.ndarray,
-    y: np.ndarray,
-    feat_idx: int,
-    n_quantiles: int = 4,
-    metrics_to_consider: list = None,
-) -> tuple:
-    X = check_array(X)
-    feature_labels = [f"Feature_{i}" for i in range(X.shape[1])]
-    feature_name = f"Feature_{feat_idx}"
+# def assemble_best_classifier(
+#     clf: BaseEstimator,
+#     X: np.ndarray,
+#     y: np.ndarray,
+#     feat_idx: int,
+#     n_quantiles: int = 4,
+#     metrics_to_consider: list = None,
+# ) -> tuple:
+#     X = check_array(X)
+#     feature_labels = [f"Feature_{i}" for i in range(X.shape[1])]
+#     feature_name = f"Feature_{feat_idx}"
 
-    if metrics_to_consider is None:
-        metrics_to_consider = _ALL_METRICS
+#     if metrics_to_consider is None:
+#         metrics_to_consider = _ALL_METRICS
 
-    X_df = pd.DataFrame(X, columns=feature_labels)
-    y_df = pd.DataFrame(y, columns=["Target"])
-    quantiles = pd.qcut(X_df[feature_name], q=n_quantiles)
+#     X_df = pd.DataFrame(X, columns=feature_labels)
+#     y_df = pd.DataFrame(y, columns=["Target"])
+#     quantiles = pd.qcut(X_df[feature_name], q=n_quantiles)
 
-    X_train, X_test, y_train, y_test = train_test_split(
-        X_df, y_df, test_size=0.33, stratify=quantiles
-    )
+#     X_train, X_test, y_train, y_test = train_test_split(
+#         X_df, y_df, test_size=0.33, stratify=quantiles
+#     )
 
-    clf.fit(X_train, y_train.to_numpy().ravel())
-    grouped_test_data = X_test.groupby(quantiles, observed=False)
+#     clf.fit(X_train, y_train.to_numpy().ravel())
+#     grouped_test_data = X_test.groupby(quantiles, observed=False)
 
-    quantile_scores = []
-    for metric in metrics_to_consider:
-        scores_for_metric = [
-            accuracy_score(
-                y_test.loc[subdf.index], clf.predict(subdf.to_numpy(), metric=metric)
-            )
-            for _, subdf in grouped_test_data
-        ]
-        quantile_scores.append(scores_for_metric)
+#     quantile_scores = []
+#     for metric in metrics_to_consider:
+#         scores_for_metric = [
+#             accuracy_score(
+#                 y_test.loc[subdf.index], clf.predict(subdf.to_numpy(), metric=metric)
+#             )
+#             for _, subdf in grouped_test_data
+#         ]
+#         quantile_scores.append(scores_for_metric)
 
-    quantile_scores = np.array(quantile_scores) * 100
-    quantile_scores_df = pd.DataFrame(
-        data=quantile_scores,
-        index=metrics_to_consider,
-        columns=[f"Quantile {i+1}" for i in range(n_quantiles)],
-    )
+#     quantile_scores = np.array(quantile_scores) * 100
+#     quantile_scores_df = pd.DataFrame(
+#         data=quantile_scores,
+#         index=metrics_to_consider,
+#         columns=[f"Quantile {i+1}" for i in range(n_quantiles)],
+#     )
 
-    best_metrics_per_quantile = quantile_scores_df.idxmax()
+#     best_metrics_per_quantile = quantile_scores_df.idxmax()
 
-    # todo for pred during best:
-    # loop through each metric, merge quantiles for each metric
-    # pred on this
+#     # todo for pred during best:
+#     # loop through each metric, merge quantiles for each metric
+#     # pred on this
 
-    # alt, but slower:
-    # loop through each quantile, and append pred
+#     # alt, but slower:
+#     # loop through each quantile, and append pred
 
-    return quantile_scores_df, best_metrics_per_quantile
+#     return quantile_scores_df, best_metrics_per_quantile