assignment sklearn

sklearn_questions.py

@@ -48,7 +48,6 @@
 to compute distances between 2 sets of samples.
 """
 import numpy as np
-import pandas as pd
 
 from sklearn.base import BaseEstimator
 from sklearn.base import ClassifierMixin
@@ -59,6 +58,8 @@
 from sklearn.utils.validation import check_array
 from sklearn.utils.multiclass import check_classification_targets
 from sklearn.metrics.pairwise import pairwise_distances
+from sklearn.utils.multiclass import unique_labels
+from sklearn.metrics import accuracy_score
 
 
 class KNearestNeighbors(BaseEstimator, ClassifierMixin):
@@ -82,6 +83,12 @@ def fit(self, X, y):
         self : instance of KNearestNeighbors
             The current instance of the classifier
         """
+        X, y = check_X_y(X, y)
+        check_classification_targets(y)
+        self.X_ = X
+        self.y_ = y
+        self.classes_ = unique_labels(y)
+        self.n_features_in_ = X.shape[1]
         return self
 
     def predict(self, X):
@@ -97,7 +104,18 @@ def predict(self, X):
         y : ndarray, shape (n_test_samples,)
             Predicted class labels for each test data sample.
         """
-        y_pred = np.zeros(X.shape[0])
+        X = check_array(X)
+        check_is_fitted(self)
+        distances = pairwise_distances(X, self.X_)
+        ord = np.argsort(distances, axis=1)[:, : self.n_neighbors]
+        ord = self.y_[ord]
+        y_pred = np.apply_along_axis(
+            lambda x: np.unique(x, return_counts=True)[0][
+                np.argmax(np.unique(x, return_counts=True)[1])
+            ],
+            axis=1,
+            arr=ord,
+        )
         return y_pred
 
     def score(self, X, y):
@@ -115,7 +133,8 @@ def score(self, X, y):
         score : float
             Accuracy of the model computed for the (X, y) pairs.
         """
-        return 0.
+        y_pred = self.predict(X)
+        return accuracy_score(y_pred, y)
 
 
 class MonthlySplit(BaseCrossValidator):
@@ -134,7 +153,7 @@ class MonthlySplit(BaseCrossValidator):
         To use the index as column just set `time_col` to `'index'`.
     """
 
-    def __init__(self, time_col='index'):  # noqa: D107
+    def __init__(self, time_col="index"):  # noqa: D107
         self.time_col = time_col
 
     def get_n_splits(self, X, y=None, groups=None):
@@ -155,7 +174,14 @@ def get_n_splits(self, X, y=None, groups=None):
         n_splits : int
             The number of splits.
         """
-        return 0
+        if self.time_col == "index":
+            X = X.reset_index()
+        self.X_time = X[self.time_col]
+
+        if X[self.time_col].dtype != "datetime64[ns]":
+            raise ValueError("datetime")
+
+        return len(self.X_time.dt.to_period("M").unique()) - 1
 
     def split(self, X, y, groups=None):
         """Generate indices to split data into training and test set.
@@ -178,11 +204,12 @@ def split(self, X, y, groups=None):
             The testing set indices for that split.
         """
 
-        n_samples = X.shape[0]
         n_splits = self.get_n_splits(X, y, groups)
+        X = X.reset_index()
+
+        isorted = X.resample("M", on=self.time_col).apply(lambda x: x.index)
+        isorted.index = isorted.index.to_period("M")
         for i in range(n_splits):
-            idx_train = range(n_samples)
-            idx_test = range(n_samples)
-            yield (
-                idx_train, idx_test
-            )
+            idx_train = np.array(isorted[isorted.index[i]])
+            idx_test = np.array(isorted[isorted.index[i + 1]])
+            yield (idx_train, idx_test)