87 lines
3.4 KiB
Python
87 lines
3.4 KiB
Python
|
import pandas as pd
|
||
|
|
import numpy as np
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
import seaborn as sns
|
||
|
|
import sklearn
|
||
|
|
from sklearn.neural_network import MLPClassifier
|
||
|
|
import argparse
|
||
|
|
|
||
|
|
from sklearn.preprocessing import (LabelEncoder,
|
||
|
|
StandardScaler,
|
||
|
|
MinMaxScaler,
|
||
|
|
RobustScaler)
|
||
|
|
from sklearn.model_selection import train_test_split, GridSearchCV, StratifiedKFold, learning_curve, ShuffleSplit
|
||
|
|
|
||
|
|
|
||
|
|
def get_arguments():
|
||
|
|
parser = argparse.ArgumentParser()
|
||
|
|
|
||
|
|
parser.add_argument('--id_pred', type=int, default=1, help='Какой id из тестовой выборки будем предсказывать')
|
||
|
|
|
||
|
|
args = parser.parse_args()
|
||
|
|
return args
|
||
|
|
|
||
|
|
|
||
|
|
def str_features_to_numeric(data):
|
||
|
|
# Преобразовывает все строковые признаки в числовые.
|
||
|
|
|
||
|
|
# Определение категориальных признаков
|
||
|
|
categorical_columns = []
|
||
|
|
numerics = ['int8', 'int16', 'int32', 'int64', 'float16', 'float32', 'float64']
|
||
|
|
features = data.columns.values.tolist()
|
||
|
|
for col in features:
|
||
|
|
if data[col].dtype in numerics: continue
|
||
|
|
categorical_columns.append(col)
|
||
|
|
|
||
|
|
# Кодирование категориальных признаков
|
||
|
|
for col in categorical_columns:
|
||
|
|
if col in data.columns:
|
||
|
|
le = LabelEncoder()
|
||
|
|
le.fit(list(data[col].astype(str).values))
|
||
|
|
data[col] = le.transform(list(data[col].astype(str).values))
|
||
|
|
|
||
|
|
return data
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
args = get_arguments()
|
||
|
|
|
||
|
|
data = pd.read_csv("..//heart_disease_uci.csv")
|
||
|
|
data['target'] = data['num']
|
||
|
|
data = data.drop(columns=['id', 'dataset', 'num'])
|
||
|
|
|
||
|
|
data_wo_null = data.dropna()
|
||
|
|
print(len(data_wo_null))
|
||
|
|
data_wo_null.head(3)
|
||
|
|
|
||
|
|
encoded_data_wo_null = str_features_to_numeric(data_wo_null)
|
||
|
|
|
||
|
|
scaler = StandardScaler()
|
||
|
|
new_data = pd.DataFrame(scaler.fit_transform(encoded_data_wo_null), columns = encoded_data_wo_null.columns)
|
||
|
|
|
||
|
|
dataset = data_wo_null.copy() # original data
|
||
|
|
target_name = 'target'
|
||
|
|
target = data_wo_null.pop(target_name)
|
||
|
|
|
||
|
|
X_train, X_test, y_train, y_test = train_test_split(new_data, target, test_size=0.2, random_state=42)
|
||
|
|
|
||
|
|
clf = MLPClassifier(random_state=42, max_iter=300, hidden_layer_sizes=(100)).fit(X_train, y_train)
|
||
|
|
print("---"*15, " MLPClassifier(100) ", "---"*15)
|
||
|
|
print(f"Accuracy: {clf.score(X_test, y_test)}")
|
||
|
|
|
||
|
|
clf2 = MLPClassifier(random_state=42, max_iter=300, hidden_layer_sizes=(300, 100)).fit(X_train, y_train)
|
||
|
|
print("---"*15, " MLPClassifier(300, 100) ", "---"*15)
|
||
|
|
print(f"Accuracy: {clf2.score(X_test, y_test)}")
|
||
|
|
|
||
|
|
clf3 = MLPClassifier(random_state=42, max_iter=300, hidden_layer_sizes=(150, 100, 50, 50)).fit(X_train, y_train)
|
||
|
|
print("---"*15, " MLPClassifier(150, 100, 50, 50) ", "---"*15)
|
||
|
|
print(f"Accuracy: {clf3.score(X_test, y_test)}")
|
||
|
|
|
||
|
|
clf4 = MLPClassifier(random_state=42, max_iter=300, hidden_layer_sizes=(100, 400, 600, 400, 100)).fit(X_train, y_train)
|
||
|
|
print("---"*15, " MLPClassifier(100, 400, 600, 400, 100) ", "---"*15)
|
||
|
|
print(f"Accuracy: {clf4.score(X_test, y_test)}")
|
||
|
|
|
||
|
|
print("---"*15, f" Предсказание элемента под id = {args.id_pred}", "---"*15)
|
||
|
|
print(f"Предсказанное значение: {clf3.predict(np.array(list(X_test.iloc[args.id_pred])).reshape(1, -1))}")
|
||
|
|
print(f"Настоящее значение {y_test.iloc[args.id_pred]}")
|