Deepak Karkala deepak-karkala

Masters degree from EPFL Switzerland in Data Science, looking for full time, contract or freelancing roles as Machine Learning Engineer, Data Scientist.

9 followers · 0 following

View GitHub Profile

Recently created

Least recently created

Recently updated

Least recently updated

deepak-karkala / word2vec_import.py

Last active December 7, 2023 11:00

Word2vec Model: Import libraries

	import random
	import numpy as np
	import StanfordSentiment
	import matplotlib
	import matplotlib.pyplot as plt
	import time

deepak-karkala / abtesting_chisq_distance.py

Created December 29, 2020 06:46

# A/B Testing: Conversion Rate: Distance between chi-squared distributions

	# A/B Testing: Conversion Rate: Distance between chi-squared distributions
	from scipy.stats import chi2

	T = np.array([165, 165, 9835, 9835])
	O = np.array([150, 180, 9850, 9800])

	D = np.sum(np.square(T-O)/T)

	pvalue = chi2.sf(D, df=1)

deepak-karkala / abtesting_normal_ztest.py

Created December 29, 2020 06:43

Z-test for A/B testing

	# A/B testing: Z-test for Booking time (Normal Distribution)
	from scipy.stats import norm

	mu_A, std_A, n_A = 300, 105, 10000
	mu_B, std_B, n_B = 296, 120, 10000

	Z = (mu_A - mu_B)/np.sqrt(std_B2/n_B + std_A2/n_A)
	pvalue = norm.sf(Z)

deepak-karkala / flask_restapi_predict.py

Created December 28, 2020 14:32

REST API Service to get Price Predictions for Airbnb listings

	# REST API Service to get Price Predictions for Airbnb listings
	@app.route("/predict", methods=["POST"])
	def predict():

	# initialize the data dictionary that will be returned from the view
	data = {"success": False}

	# ensure an image was properly uploaded to our endpoint
	if flask.request.method == "POST":
	data["predictions"] = []

deepak-karkala / flask_webapp_airbnb_predict.py

Created December 28, 2020 13:37

FLASK Webapp for serving price Predictions for Airbnb listings

	# FLASK Webapp for serving price Predictions for Airbnb listings
	import os, sys
	sys.path.append(".")
	import webapp_predict_price

	import pickle
	from flask import Flask
	import flask
	import sklearn
	import joblib

deepak-karkala / flask_webapp_segmentation.py

Created December 21, 2020 07:08

FLASK Webapp for Image Segmentation Model

	# FLASK Webapp for Image Segmentation Model

	import os, sys, io
	sys.path.append(".")
	import webapp

	from flask import Flask
	import flask
	import numpy as np
	import pandas as pd

deepak-karkala / rest_api_service.py

Created December 21, 2020 06:35

Serve Model predictions using REST API

	# Serve Model predictions using REST API

	# Predict and return JSON data
	@app.route("/predict", methods=["POST"])
	def predict():
	# initialize the data dictionary that will be returned from the view
	data = {"success": False}

	# ensure an image was properly uploaded to our endpoint
	if flask.request.method == "POST":

deepak-karkala / tf_model_saving.py

Created December 20, 2020 19:30

Saving Tensorflow models for serving

	# Saving Tensorflow models for serving

	# Option 1: SavedModel format
	# Save model
	model.save('saved_model/model')
	# Load model
	loaded_model = tf.keras.models.load_model('saved_model/model')

	# Option 2: .h5 format
	# Save model

deepak-karkala / tf_model_quantisation.py

Created December 20, 2020 19:25

Model quantisation using TFLite

	# Model quantisation using TFLite
	save_model_path = "/tmp/"

	# Save original model in tflite format
	tflite_models_dir = pathlib.Path(save_model_path)
	tflite_models_dir.mkdir(exist_ok=True, parents=True)
	converter = tf.lite.TFLiteConverter.from_keras_model(model)
	tflite_model = converter.convert()
	tflite_model_file = tflite_models_dir/"model.tflite"
	print(tflite_model_file.write_bytes(tflite_model))

deepak-karkala / tf_logging_data_to_tensorboard.py

Created December 20, 2020 19:15

Logging custom data to tensorboard

	### Tensorboard callbacks
	# Log IoU at end of epoch
	def log_epoch_metrics(epoch, logs):
	# Log directory
	logdir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
	file_writer = tf.summary.create_file_writer(logdir + "/fit")
	file_writer.set_as_default()

	# Intersection Over Union metric
	m = tf.keras.metrics.MeanIoU(num_classes=len(LABEL_NAMES))

NewerOlder