KI-KNN

import pandas as pd
import numpy as np
from pathlib import Path
from os import chdir
import os
import csv
from tensorflow import keras
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, StandardScaler
from keras import models
from keras import layers
from keras import optimizers
import matplotlib.pyplot as plt
from sklearn.metrics import classification_report
import constants
from pandas import datetime

# splitting of dataset into train and test dataset

def train_test_data_split(X, y):
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20)
    print (X_train[0].shape)
    return X_train, X_test, y_train, y_test

# creating a model
def create_and_compile_model():
    print("Creating a Model")
    from keras.models import Sequential
    from keras.layers import Conv2D, Dense, MaxPooling2D, Dropout, Flatten, BatchNormalization
    model = models.Sequential()
    model.add(Conv2D(32, kernel_size=(3, 3), activation="relu", input_shape=(constants.N_FEATURE, constants.FEATURE_MAX_LEN, constants.CHANNELS)))
    model.add(Conv2D(32, kernel_size=(3, 3), activation="relu"))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Conv2D(64, kernel_size=(3, 3), activation="relu"))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Dropout(0.5))
    model.add(Flatten())
    model.add(Dense(128, activation="relu"))
    model.add(Dense(constants.OUTPUT_LAYER_DIMENSIONS, activation='softmax'))
    print("Compiling a Model")
    optimizer = keras.optimizers.RMSprop()
    model.compile(optimizer=optimizer, loss=constants.LOSS_FUNCTION_SPARSE, metrics=[constants.ACCURACY_METRICS])
    print(model.summary())
    return model

    def preprocessing_csv_data():
    print("Reading Features... ")
    data = pd.read_csv(constants.FEATURES_CSV_NAME)
    data.head()
# Dropping unnecessary columns (Column Filename is dropped)
    data = data.drop(['filename'], axis=1)
    data.head()
    return data

# Extracting classes/label column as y from csv and converting string labels to numbers using LabelEncoder 
    def encode_labels(data):
    list = data.iloc[:, -1]
    encoder = LabelEncoder()
    target_labels = encoder.fit_transform(list)
    return target_labels, encoder

def train_and_save_model(model, X_train, y_train, X_test, y_test):
    logdir = constants.LOG_DIR_PATH
    tensorboard_callback = keras.callbacks.TensorBoard(log_dir=logdir)
    print("Start Training...")
    history = model.fit(X_train, y_train, batch_size=32, epochs=35, validation_data=(X_test, y_test), callbacks=[tensorboard_callback])
# Saving the trained model to avoid re-training
    model.save(constants.TRAINED_MODEL)
    return history

def predict(X_test, y_test):
    print("Predictions.....")
    predictions = np.argmax(model.predict(X_test), axis=-1)
    target_names = [constants.LIGHT_WEIGHT, constants.MEDIUM_WEIGHT, constants.HEAVY_WEIGHT,constants.TWO_WHEELED, constants.RAIL_BOUND]
    print(classification_report(y_test, predictions, target_names=target_names))

def plot_model_accuracy(history):
    # Plot graph Model Accuracy
    plt.plot(history.history['accuracy'])
    plt.plot(history.history['val_accuracy'])
    plt.title('Model Accuracy')
    plt.ylabel('Accuracy')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Test'], loc='upper left')
    plt.show()

def plot_model_loss(history):
    # Plot graph Model Loss
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('Model loss')
    plt.ylabel('Loss')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Test'], loc='upper right')
    plt.show()

# Changing Directory to Training Dataset Folder
chdir(constants.TRAINING_DATA_DIRECTORY_NAME)
trainingDataDir = Path.cwd()
trainingDataSubDirs = os.listdir(trainingDataDir)
chdir("..")
if os.path.isfile(constants.FEATURES_CSV_NAME):
    print("features.csv already exists, skip extraction")
else:
    extract_features(trainingDataDir, trainingDataSubDirs)



data = preprocessing_csv_data()
target_labels, encoder = encode_labels(data)
X = normalize_data(data)
X_train, X_test, y_train, y_test = train_test_data_split(X, target_labels)
model = create_and_compile_model()
history = train_and_save_model(model, X_train, y_train, X_test, y_test)
predict(X_test, y_test)
plot_model_accuracy(history)
plot_model_loss(history)

def predict(X_test, y_test):
    print("Predictions.....")
    predictions = np.argmax(model.predict(X_test), axis=-1)
    target_names = [constants.0, constants.1]
    print(classification_report(y_test, predictions, target_names=target_names))

def normalize_data(data):
    # normalizing - Extracting Remaining Columns as X and normalizing them to a common scale
    scaler = StandardScaler()
    print (data.iloc[:, :-1])
    X = scaler.fit_transform(np.array(data.iloc[:, :-1], dtype=float))
    X = X.reshape(-1, constants.N_, constants.MAX_LEN, constants.CHANNELS)
    return X