import pandas as pd

import numpy as np

import seaborn as sns

import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import LabelEncoder

from sklearn.metrics import accuracy_score, confusion_matrix, ConfusionMatrixDisplay

import tensorflow

from tensorflow import keras

from tensorflow.keras import Sequential

from tensorflow.keras.layers import Dense

from tensorflow.keras.utils import to_categorical

data = pd.read_csv("iris.csv")

le = LabelEncoder()

data['Species'] = le.fit_transform(data['Species'])

num = le.fit_transform(data['Species'])

twoDlabel = to_categorical(num)

threeDlabel = np.expand_dims(twoDlabel, axis=1)

feature_cols = ["SepalLengthCm", "SepalWidthCm", "PetalLengthCm", "PetalWidthCm"]

x = data[feature_cols]

y = twoDlabel

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=24)

model = Sequential()

model.add(Dense(64, activation='relu', input_dim=4))

model.add(Dense(128, activation='relu'))

model.add(Dense(3, activation='softmax'))

model.summary()

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

history = model.fit(x_train, y_train, epochs=100)

y_test = np.argmax(y_test, axis=1)

y_predprob = model.predict(x_test)

y_pred = np.argmax(y_predprob, axis=1)

cn = confusion_matrix(y_test, y_pred)

print(cn)

print(y_test.shape)

f, ax = plt.subplots(figsize=(5,5))

sns.heatmap(cn, annot=True, linewidths=0.5, linecolor='pink', fmt=".0f", ax=ax)

plt.xlabel("y_pred")

plt.ylabel("y_test")