#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Mar 23 13:36:46 2022

@author: tanu
"""
#https://umap-learn.readthedocs.io/en/latest/auto_examples/plot_feature_extraction_classification.html
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC

from umap import UMAP

# Make a toy dataset
X, y = make_classification(
    n_samples=1000,
    n_features=300,
    n_informative=250,
    n_redundant=0,
    n_repeated=0,
    n_classes=2,
    random_state=1212,
)

# Split the dataset into a training set and a test set
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

# Classification with a linear SVM
svc = LinearSVC(dual=False, random_state=123)
params_grid = {"C": [10 ** k for k in range(-3, 4)]}
clf = GridSearchCV(svc, params_grid)
clf.fit(X_train, y_train)
print(
    "Accuracy on the test set with raw data: {:.3f}".format(clf.score(X_test, y_test))
)

# Transformation with UMAP followed by classification with a linear SVM
umap = UMAP(random_state=456)
pipeline = Pipeline([("umap", umap), ("svc", svc)])
params_grid_pipeline = {
    "umap__n_neighbors": [5, 20],
    "umap__n_components": [15, 25, 50],
    "svc__C": [10 ** k for k in range(-3, 4)],
}


clf_pipeline = GridSearchCV(pipeline, params_grid_pipeline)
clf_pipeline.fit(X_train, y_train)
print(
    "Accuracy on the test set with UMAP transformation: {:.3f}".format(
        clf_pipeline.score(X_test, y_test)
    )
)