Able to predict

test/data_weather.csv

@@ -0,0 +1,15 @@
+outlook,temperature,humidity,windy,play
+sunny,85,85,FALSE,no
+sunny,80,90,TRUE,no
+overcast,83,86,FALSE,yes
+rainy,70,96,FALSE,yes
+rainy,68,80,FALSE,yes
+rainy,65,70,TRUE,no
+overcast,64,65,TRUE,yes
+sunny,72,95,FALSE,no
+sunny,69,70,FALSE,yes
+rainy,75,80,FALSE,yes
+sunny,75,70,TRUE,yes
+overcast,72,90,TRUE,yes
+overcast,81,75,FALSE,yes
+rainy,71,91,TRUE,no

testmodel.py

@@ -2,12 +2,32 @@
 from model.util.layer import Layer
 from model.util.node import Node
 from model.util.activation_fun import sigmoid
+
 import matplotlib.pyplot as plt
+from util.preprocess import preprocess
 import numpy as np
 
 x = [[0.1, 0.9]]
 y = [[0.9]]
-epochs = 1000
+epochs = 100
+
+# X, y = preprocess('./test/data_weather.csv')
+
+model = Sequential([
+  Layer(2),
+  Layer(2),
+  Layer(2),
+  Layer(2),
+  Layer(1),
+])
+
+model.compile()
+model.fit(
+  x,
+  y,
+  epochs=epochs,
+  batch_size=2
+)
 
 # n11 = Node(sigmoid, [-0.2, 0.1], 0.1)
 # n12 = Node(sigmoid, [-0.1, 0.3], 0.1)
@@ -25,23 +45,23 @@
 # ])
 
 # versi weights random
-model = Sequential([
-  Layer(2),
-  Layer(1),
-])
+# model = Sequential([
+#   Layer(2),
+#   Layer(1),
+# ])
 
-model.compile()
-model.fit(
-  x,
-  y,
-  epochs=epochs,
-  batch_size=1
-)
+# model.compile()
+# model.fit(
+#   x,
+#   y,
+#   epochs=epochs,
+#   batch_size=1
+# )
 
 # plotting cost (error)
-times = [i for i in range(epochs)]
+times = [i for i in range(len(model.optimizer.error_list))]
 
 plt.plot(times, model.optimizer.error_list)
 plt.show()
 
-print('\n\noutput predict {}: {}'.format(x[0], model.predict(x)))
+print('\n\noutput predict {}: {}'.format(x[0], model.predict([x[0]])))

util/preprocess.py

@@ -0,0 +1,17 @@
+from sklearn.preprocessing import LabelEncoder
+from util.read_file import read_file
+
+def preprocess(path):
+  X, y = read_file(path)
+
+  encoder = LabelEncoder()
+
+  X[:, 0], X[:, 3] = encoder.fit_transform(X[:, 0]), encoder.fit_transform(X[:, 3])
+  y = encoder.fit_transform(y)
+
+  X = X.tolist()
+  y = y.tolist()
+
+  y = [[e] for e in y]
+
+  return X, y

util/read_file.py

@@ -1,15 +1,6 @@
 import pandas as pd
 from sklearn.preprocessing import LabelEncoder
 
-encoder = LabelEncoder()
-
 def read_file(path):
   df_weather = pd.read_csv(path)
-  return df_weather.drop(['play'], axis=1).values, df_weather['play'].values
-
-X, y = read_file('../test/data_weather.csv')
-X[:, 0], X[:, 3] = encoder.fit_transform(X[:, 0]), encoder.fit_transform(X[:, 3])
-y = encoder.fit_transform(y)
-
-print(X)
-print(y)
+  return df_weather.drop(['play'], axis=1).values, df_weather['play'].values