import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import tensorflow as tf
from imblearn.over_sampling import SMOTE

smote = SMOTE(random_state=42)
data = pd.read_csv('data.csv', sep=';')

print('Total rows:', len(data))
print('Rows with medal:', len(data.dropna(subset=['Medal'])))


data = pd.get_dummies(data, columns=['Sex', 'Medal'])

data = data.drop(columns=['Name', 'Team', 'NOC', 'Games', 'Year', 'Season', 'City', 'Sport', 'Event'])

scaler = MinMaxScaler()
data = pd.DataFrame(scaler.fit_transform(data), columns=data.columns)

X = data.filter(regex='Sex|Age')
y = data.filter(regex='Medal')
y = pd.get_dummies(y)

X = X.fillna(0)
y = y.fillna(0)

y = y.values

X_resampled, y_resampled = smote.fit_resample(X, y)
X_train, X_test, y_train, y_test = train_test_split(X_resampled, y_resampled, test_size=0.2, random_state=42)

model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(64, input_dim=X_train.shape[1], activation='relu')) 
model.add(tf.keras.layers.Dense(32, activation='relu'))
model.add(tf.keras.layers.Dense(y.shape[1], activation='softmax')) 

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(X_train, y_train, epochs=10, batch_size=32)
loss, accuracy = model.evaluate(X_test, y_test)
print('Test accuracy:', accuracy)

model.save('model.h5')