Import the libraries¶
In [1]:
import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
Read the input data¶
In [2]:
df = pd.read_csv('Iris.csv')
Take a look at the data¶
Take a look at the first few rows¶
In [3]:
print(df.head())
Take a look at the number of rows and columns¶
In [4]:
rows, cols = df.shape
print(rows)
print(cols)
Convert string values to numeric values¶
In [5]:
label_names = df['Species'].unique()
print(label_names)
In [6]:
index_and_label = list(enumerate(label_names))
print(index_and_label)
In [7]:
label_to_index = dict((label, index) for index, label in index_and_label)
print(label_to_index)
In [8]:
df = df.replace(label_to_index)
print(df.head())
Shuffle the data¶
In [9]:
df = df.sample(frac=1.0)
Split the data into training and testing data¶
In [10]:
train_data = df.iloc[:120, :]
test_data = df.iloc[120:, :]
x_train = train_data.iloc[:, 1:-1]
y_train = train_data.iloc[:, -1:]
x_test = test_data.iloc[:, 1:-1]
y_test = test_data.iloc[:, -1:]
In [11]:
print(len(train_data))
print(len(test_data))
Scale the numerical inputs¶
In [12]:
def scale_column(train_data, test_data, column):
min_value = train_data[column].min()
max_value = train_data[column].max()
train_data[column] = (train_data[column] - min_value)/(max_value - min_value)
test_data[column] = (test_data[column] - min_value)/(max_value - min_value)
In [13]:
scale_column(x_train, x_test, "SepalLengthCm")
scale_column(x_train, x_test, "SepalWidthCm")
scale_column(x_train, x_test, "PetalLengthCm")
scale_column(x_train, x_test, "PetalWidthCm")
Take a look at the final transformed data¶
In [14]:
print(x_train.head())
Convert to Numpy arrays¶
In [15]:
x_train = x_train.to_numpy()
y_train = y_train.to_numpy()
x_test = x_test.to_numpy()
y_test = y_test.to_numpy()
In [16]:
print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)
Build the neural network model¶
In [17]:
model = tf.keras.Sequential()
model.add(tf.keras.layers.Input(shape=[4]))
model.add(tf.keras.layers.Dense(units=64, activation='relu'))
model.add(tf.keras.layers.Dense(units=3, activation='softmax'))
model.summary()
Choose the loss function and optimizer¶
In [18]:
model.compile(optimizer='Adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
Start the training process¶
In [19]:
history = model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=75)
Evaluate with test data¶
In [20]:
test_loss, test_acc = model.evaluate(x_test, y_test)
print(test_acc)
Plot training and validation loss¶
In [21]:
plt.figure(figsize=(20, 10))
plt.subplot(2, 2, 1)
plt.plot(history.history['loss'])
plt.subplot(2, 2, 2)
plt.plot(history.history['accuracy'])
plt.subplot(2, 2, 3)
plt.plot(history.history['val_loss'])
plt.subplot(2, 2, 4)
plt.plot(history.history['val_accuracy'])
plt.show()
