From 27867a0a88875461bb369ca2763a70dc0175aef0 Mon Sep 17 00:00:00 2001 From: Sephine-1st <154244803+Sephine-1st@users.noreply.github.com> Date: Sat, 23 Dec 2023 00:07:11 +0100 Subject: [PATCH] Add files via upload UP my solution --- sklearn_questions.py | 405 +++++++++++++++++++++++-------------------- 1 file changed, 217 insertions(+), 188 deletions(-) diff --git a/sklearn_questions.py b/sklearn_questions.py index fa02e0d..30a7930 100644 --- a/sklearn_questions.py +++ b/sklearn_questions.py @@ -1,188 +1,217 @@ -"""Assignment - making a sklearn estimator and cv splitter. - -The goal of this assignment is to implement by yourself: - -- a scikit-learn estimator for the KNearestNeighbors for classification - tasks and check that it is working properly. -- a scikit-learn CV splitter where the splits are based on a Pandas - DateTimeIndex. - -Detailed instructions for question 1: -The nearest neighbor classifier predicts for a point X_i the target y_k of -the training sample X_k which is the closest to X_i. We measure proximity with -the Euclidean distance. The model will be evaluated with the accuracy (average -number of samples corectly classified). You need to implement the `fit`, -`predict` and `score` methods for this class. The code you write should pass -the test we implemented. You can run the tests by calling at the root of the -repo `pytest test_sklearn_questions.py`. Note that to be fully valid, a -scikit-learn estimator needs to check that the input given to `fit` and -`predict` are correct using the `check_*` functions imported in the file. -You can find more information on how they should be used in the following doc: -https://scikit-learn.org/stable/developers/develop.html#rolling-your-own-estimator. -Make sure to use them to pass `test_nearest_neighbor_check_estimator`. - - -Detailed instructions for question 2: -The data to split should contain the index or one column in -datatime format. Then the aim is to split the data between train and test -sets when for each pair of successive months, we learn on the first and -predict of the following. For example if you have data distributed from -november 2020 to march 2021, you have have 4 splits. The first split -will allow to learn on november data and predict on december data, the -second split to learn december and predict on january etc. - -We also ask you to respect the pep8 convention: https://pep8.org. This will be -enforced with `flake8`. You can check that there is no flake8 errors by -calling `flake8` at the root of the repo. - -Finally, you need to write docstrings for the methods you code and for the -class. The docstring will be checked using `pydocstyle` that you can also -call at the root of the repo. - -Hints ------ -- You can use the function: - -from sklearn.metrics.pairwise import pairwise_distances - -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 - -from sklearn.model_selection import BaseCrossValidator - -from sklearn.utils.validation import check_X_y, check_is_fitted -from sklearn.utils.validation import check_array -from sklearn.utils.multiclass import check_classification_targets -from sklearn.metrics.pairwise import pairwise_distances - - -class KNearestNeighbors(BaseEstimator, ClassifierMixin): - """KNearestNeighbors classifier.""" - - def __init__(self, n_neighbors=1): # noqa: D107 - self.n_neighbors = n_neighbors - - def fit(self, X, y): - """Fitting function. - - Parameters - ---------- - X : ndarray, shape (n_samples, n_features) - Data to train the model. - y : ndarray, shape (n_samples,) - Labels associated with the training data. - - Returns - ---------- - self : instance of KNearestNeighbors - The current instance of the classifier - """ - return self - - def predict(self, X): - """Predict function. - - Parameters - ---------- - X : ndarray, shape (n_test_samples, n_features) - Data to predict on. - - Returns - ---------- - y : ndarray, shape (n_test_samples,) - Predicted class labels for each test data sample. - """ - y_pred = np.zeros(X.shape[0]) - return y_pred - - def score(self, X, y): - """Calculate the score of the prediction. - - Parameters - ---------- - X : ndarray, shape (n_samples, n_features) - Data to score on. - y : ndarray, shape (n_samples,) - target values. - - Returns - ---------- - score : float - Accuracy of the model computed for the (X, y) pairs. - """ - return 0. - - -class MonthlySplit(BaseCrossValidator): - """CrossValidator based on monthly split. - - Split data based on the given `time_col` (or default to index). Each split - corresponds to one month of data for the training and the next month of - data for the test. - - Parameters - ---------- - time_col : str, defaults to 'index' - Column of the input DataFrame that will be used to split the data. This - column should be of type datetime. If split is called with a DataFrame - for which this column is not a datetime, it will raise a ValueError. - To use the index as column just set `time_col` to `'index'`. - """ - - def __init__(self, time_col='index'): # noqa: D107 - self.time_col = time_col - - def get_n_splits(self, X, y=None, groups=None): - """Return the number of splitting iterations in the cross-validator. - - Parameters - ---------- - X : array-like of shape (n_samples, n_features) - Training data, where `n_samples` is the number of samples - and `n_features` is the number of features. - y : array-like of shape (n_samples,) - Always ignored, exists for compatibility. - groups : array-like of shape (n_samples,) - Always ignored, exists for compatibility. - - Returns - ------- - n_splits : int - The number of splits. - """ - return 0 - - def split(self, X, y, groups=None): - """Generate indices to split data into training and test set. - - Parameters - ---------- - X : array-like of shape (n_samples, n_features) - Training data, where `n_samples` is the number of samples - and `n_features` is the number of features. - y : array-like of shape (n_samples,) - Always ignored, exists for compatibility. - groups : array-like of shape (n_samples,) - Always ignored, exists for compatibility. - - Yields - ------ - idx_train : ndarray - The training set indices for that split. - idx_test : ndarray - The testing set indices for that split. - """ - - n_samples = X.shape[0] - n_splits = self.get_n_splits(X, y, groups) - for i in range(n_splits): - idx_train = range(n_samples) - idx_test = range(n_samples) - yield ( - idx_train, idx_test - ) +"""Assignment - making a sklearn estimator and cv splitter. + +The goal of this assignment is to implement by yourself: +- a scikit-learn estimator for the KNearestNeighbors for classification + tasks and check that it is working properly. +- a scikit-learn CV splitter where the splits are based on a Pandas + DateTimeIndex. + +Detailed instructions for question 1: +The nearest neighbor classifier predicts for a point X_i the target y_k of +the training sample X_k which is the closest to X_i. We measure proximity with +the Euclidean distance. The model will be evaluated with the accuracy (average +number of samples corectly classified). You need to implement the `fit`, +`predict` and `score` methods for this class. The code you write should pass +the test we implemented. You can run the tests by calling at the root of the +repo `pytest test_sklearn_questions.py`. Note that to be fully valid, a +scikit-learn estimator needs to check that the input given to `fit` and +`predict` are correct using the `check_*` functions imported in the file. +You can find more information on how they should be used in the following doc: +https://scikit-learn.org/stable/developers/develop.html#rolling-your-own-estimator. +Make sure to use them to pass `test_nearest_neighbor_check_estimator`. + +Detailed instructions for question 2: +The data to split should contain the index or one column in +datatime format. Then the aim is to split the data between train and test +sets when for each pair of successive months, we learn on the first and +predict of the following. For example if you have data distributed from +november 2020 to march 2021, you have have 4 splits. The first split +will allow to learn on november data and predict on december data, the +second split to learn december and predict on january etc. + +We also ask you to respect the pep8 convention: https://pep8.org. This will be +enforced with `flake8`. You can check that there is no flake8 errors by +calling `flake8` at the root of the repo. + +Finally, you need to write docstrings for the methods you code and for the +class. The docstring will be checked using `pydocstyle` that you can also +call at the root of the repo. +Hints +----- +- You can use the function: +from sklearn.metrics.pairwise import pairwise_distances +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 + +from sklearn.model_selection import BaseCrossValidator + +from sklearn.utils.validation import check_X_y, check_is_fitted +from sklearn.utils.validation import check_array +from sklearn.utils.multiclass import check_classification_targets +from sklearn.metrics.pairwise import pairwise_distances + + +class KNearestNeighbors(BaseEstimator, ClassifierMixin): + """KNearestNeighbors classifier.""" + + def __init__(self, n_neighbors=1): # noqa: D107 + self.n_neighbors = n_neighbors + + def fit(self, X, y): + """Fitting function. + + Parameters + ---------- + X : ndarray, shape (n_samples, n_features) + Data to train the model. + y : ndarray, shape (n_samples,) + Labels associated with the training data. + Returns + ---------- + self : instance of KNearestNeighbors + The current instance of the classifier + """ + X, y = check_X_y(X, y) + check_classification_targets(y) + + self.n_features_in_ = X.shape[1] + self.X_ = X + self.y_ = y + self.classes_ = np.unique(y) + + return self + + def predict(self, X): + """Predict function. + + Parameters + ---------- + X : ndarray, shape (n_test_samples, n_features) + Data to predict on. + Returns + ---------- + y : ndarray, shape (n_test_samples,) + Predicted class labels for each test data sample. + """ + y_pred = np.zeros(X.shape[0]) + check_is_fitted(self) + X = check_array(X) + + distances = pairwise_distances(X, self.X_, metric="euclidean") + nearest_indices = np.argsort(distances, axis=1)[:, : self.n_neighbors] + nearest_labels = self.y_[nearest_indices] + + y_pred = np.array([max(set(labels), key=list(labels).count) + for labels in nearest_labels]) + return y_pred + + def score(self, X, y): + """Calculate the score of the prediction. + + Parameters + ---------- + X : ndarray, shape (n_samples, n_features) + Data to score on. + y : ndarray, shape (n_samples,) + target values. + Returns + ---------- + score : float + Accuracy of the model computed for the (X, y) pairs. + """ + check_is_fitted(self) + X, y = check_X_y(X, y) + # Make predictions using the trained model + y_pred = self.predict(X) + # Compute accuracy + accuracy = np.mean(y_pred == y) + return accuracy + + +class MonthlySplit(BaseCrossValidator): + """CrossValidator based on monthly split. + + Split data based on the given `time_col` (or default to index). Each split + corresponds to one month of data for the training and the next month of + data for the test. + + Parameters + ---------- + time_col : str, defaults to 'index' + Column of the input DataFrame that will be used to split the data. This + column should be of type datetime. If split is called with a DataFrame + for which this column is not a datetime, it will raise a ValueError. + To use the index as column just set `time_col` to `'index'`. + """ + + def __init__(self, time_col='index'): # noqa: D107 + self.time_col = time_col + + def get_n_splits(self, X, y=None, groups=None): + """Return the number of splitting iterations in the cross-validator. + + Parameters + ---------- + X : array-like of shape (n_samples, n_features) + Training data, where `n_samples` is the number of samples + and `n_features` is the number of features. + y : array-like of shape (n_samples,) + Always ignored, exists for compatibility. + groups : array-like of shape (n_samples,) + Always ignored, exists for compatibility. + Returns + ------- + n_splits : int + The number of splits. + """ + X = X.reset_index() + + if not pd.api.types.is_datetime64_any_dtype(X[self.time_col]): + raise ValueError("The time column is not a datetime") + + n_splits = X[self.time_col].dt.to_period("M").nunique() - 1 + return n_splits + + def split(self, X, y, groups=None): + """Generate indices to split data into training and test set. + + Parameters + ---------- + X : array-like of shape (n_samples, n_features) + Training data, where `n_samples` is the number of samples + and `n_features` is the number of features. + y : array-like of shape (n_samples,) + Always ignored, exists for compatibility. + groups : array-like of shape (n_samples,) + Always ignored, exists for compatibility. + Yields + ------ + idx_train : ndarray + The training set indices for that split. + idx_test : ndarray + The testing set indices for that split. + """ + X = X.reset_index() + + n_samples = X.shape[0] + if not pd.api.types.is_datetime64_any_dtype(X[self.time_col]): + raise ValueError("The time column is not a datetime") + + periods = X[self.time_col].dt.to_period("M") + unique_periods = np.sort(periods.unique()) + n_splits = self.get_n_splits(X, y, groups) + + for i in range(n_splits): + idx_train = range(n_samples) + idx_test = range(n_samples) + yield ( + idx_train, idx_test + ) + idx_train = np.where(periods == unique_periods[i])[0] + idx_test = np.where(periods == unique_periods[i + 1])[0] + yield (idx_train, idx_test)