grid_search.py

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.svm import SVC
import pandas as pd
import numpy as np

A = pd.read_csv('dataset_csv/dataset.csv')

m, n = A.shape
A_value = np.array(A.values[:,range(1,3)])

class_label = np.array([[]])
for i in range(m):
        if A.iloc[i]['Tekanan Tulisan'] == "Kuat":
            class_label = np.append(class_label, [1])
        elif A.iloc[i]['Tekanan Tulisan'] == "Sedang":
            class_label = np.append(class_label, [2])
        elif A.iloc[i]['Tekanan Tulisan'] == "Ringan":
            class_label = np.append(class_label, [3])

X = A[['Rerata', 'Persentase']]
y = class_label

# Split the dataset in two equal parts
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=0)

# Set the parameters by cross-validation
tuned_parameters = [{'kernel': ['rbf'], 'gamma': [1e-3, 1e-4],
                     'C': [1, 10, 100, 1000]},
                    {'kernel': ['linear'], 'C': [1, 10, 100, 1000]}]

scores = ['precision', 'recall']

for score in scores:
    print("# Tuning hyper-parameters for %s" % score)
    print()

    clf = GridSearchCV(
        SVC(), tuned_parameters, scoring='%s_macro' % score
    )
    clf.fit(X_train, y_train)

    print("Best parameters set found on development set:")
    print()
    print(clf.best_params_)
    print()
    print("Grid scores on development set:")
    print()
    means = clf.cv_results_['mean_test_score']
    stds = clf.cv_results_['std_test_score']
    for mean, std, params in zip(means, stds, clf.cv_results_['params']):
        print("%0.3f (+/-%0.03f) for %r"
              % (mean, std * 2, params))
    print()

    print("Detailed classification report:")
    print()
    print("The model is trained on the full development set.")
    print("The scores are computed on the full evaluation set.")
    print()
    y_true, y_pred = y_test, clf.predict(X_test)
    print(classification_report(y_true, y_pred))
    print()