nn

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense
from sklearn.model_selection import train_test_split

nn_0_data = pd.read_csv('nn_0.csv')
plt.scatter(nn_0_data.loc[nn_0_data['class'] == -1]['X1'].values, nn_0_data.loc[nn_0_data['class'] == -1]['X2'].values, c='r')
plt.scatter(nn_0_data.loc[nn_0_data['class'] == 1]['X1'].values, nn_0_data.loc[nn_0_data['class'] == 1]['X2'].values, c='b')
plt.show()

y = nn_0_data.loc[:,'class':]
y = y.values.ravel()
X = nn_0_data.loc[:,'X1':'X2']
X = X.values.tolist()
y = [0 if i == -1 else 1 for i in y]
X = np.array(X)
y = np.array(y)

model = Sequential()
model.add(Dense(1, input_dim=2))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())

X_train, X_test, y_train, y_test = train_test_split(X, y, shuffle=True, test_size = 0.25, random_state=42)
model.fit(X_train, y_train, epochs=10, batch_size=2)

print(X_test)
model.evaluate(X_test, y_test)
model.predict(X_test)