import pandas as pd
import numpy as np
from sklearn.ensemble import ExtraTreesClassifier
import matplotlib.pyplot as plt
from common.import_data import ImportData
if __name__ == "__main__":
data_set = ImportData()
x: np.ndarray = data_set.import_train_data()
y: np.ndarray = data_set.import_columns_train(np.array(['quality']))
name_of_columns: np.ndarray = data_set.import_names_of_columns()
model = ExtraTreesClassifier()
model.fit(x, y)
print(model.feature_importances_)
feat_importances = pd.Series(model.feature_importances_,
index=[
'fixed acidity', 'volatile acidity',
'citric acid', 'residual sugar', 'chlorides',
'free sulfur dioxide', 'total sulfur dioxide',
'density', 'ph', 'sulphates', 'alcohol'
])
feat_importances.nlargest(11).plot(kind='barh')
plt.xlabel("Znaczenie cech")
plt.show()
import numpy as np
from common.import_data import ImportData
from collections import Counter
from imblearn.under_sampling import AllKNN
if __name__ == "__main__":
data_set = ImportData()
x: np.ndarray = data_set.import_all_data()
y: np.ndarray = data_set.import_columns(np.array(['Class'])).ravel()
print('Original dataset shape %s' % Counter(y))
allknn = AllKNN()
x_res, y_res = allknn.fit_resample(x, y)
print('Reduced dataset shape %s' % Counter(y_res))
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
from common.import_data import ImportData
from sklearn.model_selection import KFold
import sklearn.metrics as metrics
if __name__ == "__main__":
data_set = ImportData()
y: np.ndarray = data_set.import_classes(['class']).ravel()
x_tmp: np.ndarray = data_set.import_columns(
'./dataset3/pokerhand.csv',
['s1', 'r1', 's2', 'r2', 's3', 'r3', 's4', 'r4', 's5', 'r5'])
kf_for_test = KFold(n_splits=10, shuffle=True)
result_tmp = next(kf_for_test.split(x_tmp), None)
x_test = x_tmp[result_tmp[1]]
y_test = y[result_tmp[1]]
kf_AllKNN = KFold(n_splits=5, shuffle=True)
#x = data_set.import_columns(['s1','r1','s2','r2','s3','r3','s4','r4','s5','r5'])
x_AllKNN: np.ndarray = data_set.import_columns(
'./dataset3/reduced_dataset_AllKNN_pokerhand.csv',
['s1', 'r1', 's2', 'r2', 's3', 'r3', 's4', 'r4', 's5', 'r5'])
#x = data_set.import_all_data()
y = data_set.import_classes_for_reduced_datasets(
'./dataset3/reduced_dataset_AllKNN_pokerhand.csv', np.array(['class']))
result_AllKNN = next(kf_AllKNN.split(x_AllKNN), None)
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
from common.import_data import ImportData
if __name__ == "__main__":
data_set = ImportData()
x_train, x_test, y_train, y_test = \
train_test_split(data_set.import_all_data(),
data_set.import_columns
(np.array(['quality'])),
test_size=0.2, random_state=13)
NN = MLPClassifier(solver='adam',
alpha=0.0001,
hidden_layer_sizes=(21, 3),
random_state=1,
max_iter=2000,
verbose=1).fit(x_train, y_train.ravel())
predictions = NN.predict(x_train)
print(predictions)
print(round(NN.score(x_test, y_test.ravel()), 4))
import numpy as np
from sklearn.model_selection import train_test_split
from common.import_data import ImportData
from sklearn.metrics import accuracy_score
from sklearn.ensemble import RandomForestClassifier
if __name__ == "__main__":
data_set = ImportData()
x_train, x_test, y_train, y_test = train_test_split(
data_set.import_all_data(),
data_set.import_columns(np.array(['Class'])),
test_size=0.2,
random_state=0)
random_forest = RandomForestClassifier(n_estimators=100)
random_forest.fit(x_train, y_train.ravel())
y_prediction = random_forest.predict(x_test)
print(y_test)
print(y_prediction)
print(accuracy_score(y_test, y_prediction.ravel()))