gistfile1.txt

import argparse
from sklearn.model_selection import validation_curve, GridSearchCV, learning_curve, train_test_split
from sklearn.metrics import make_scorer, accuracy_score, f1_score, confusion_matrix
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn import datasets
from sklearn import tree
import numpy as np
from collections import namedtuple
import matplotlib.pyplot as plt
from yellowbrick.datasets import load_occupancy
from yellowbrick.model_selection import ValidationCurve
from yellowbrick.classifier import ClassificationReport
import sklearn


#%% Load data
RANDOM_SEED = 123
X, y = sklearn.datasets.make_classification(n_samples=4400, n_features=500, n_informative=5, n_redundant=15)
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=RANDOM_SEED)


#%% Base model
clf = tree.DecisionTreeClassifier()
model = Pipeline([('Scale', StandardScaler()), ("DecisionTree", clf)])
params_grid = {
    "DecisionTree__max_depth": np.arange(1, 50, 1),
    "DecisionTree__min_samples_split": np.arange(2, 10, 1)
}
scorer = "accuracy"

#%% Grid search
cv = GridSearchCV(model, params_grid, scoring=scorer, cv=5, verbose=5, n_jobs=-1)
cv.fit(x_train, y_train)
print("**** Grid Search ****")
print(f"Best parameters: {cv.best_params_}")