import numpy as np
from sklearn.datasets import load_iris

iris =load_iris()
print(iris.DESCR)
X = iris.data
y = iris.target

from keras.utils import to_categorical

y = to_categorical(y)

from sklearn.model_selection import train_test_split


X_train, X_test ,y_train,y_test =train_test_split(X,y,test=0.33,random_state=42)

from sklearn.preprocessing import MinMaxScaler

scaler_object =MinMAxScaler()
scaler_object.fit(X_train)

scaled_X_train = scaler_object.transform(X_train)
scaled_X_test = scaler_object.transform(X_test)

from Keras.models import Sequential
from keras.layers import Dense


model = Sequential()
model.add(Dense(8,input_dim=4,activation='relu'))
model.add(Dense(8,input_dim=4,activation='relu'))
model.add(Dense(3,activation='softmax'))
model.compile(loss='categorical_crossentropy,optmizer='adam',metrics=['accuracy'])

model.summary

model.fit(scaled_X_train,y_train,epocks=150,verbose=2)

# Evaluate Our NN
predictions = model.predict_classes(scaled_X_text)

y_test.argmax(axis=1) ## to get the index potion

from sklearn.metrics import confsion_matrix, classification_report, accuracy_score

confusion_matrix(y_test.argmax(axis=1),predictions)

print(classification_report(y_test.argmax(axis=1),predictions)

accuracy_score(y_test.argmax(axis=1),predictions)

model.save('file location\name.h5')

from keras.models import load_model
new_model = load_model('file location\name.h5')

new_model.predict_classes(scaled_X_test)