Learn Data Science using Python

Another post starts with you beautiful people! In  previous post  we have learnt keras workflow. In this post we will understand how to solve a image related problem with a simple neural network model using keras. For this exercise we will use  MNIST hand written digit dataset .  The MNIST database of handwritten digits has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from NIST. The digits have been size-normalized and centered in a fixed-size image. This is a very popular dataset to get started with images. You can download this dataset from this link . In this dataset, each digit shows an image and each image is composed of 28 pixel by 28 pixel grid. The image is represented by how dark each pixel is. So zero will be darkest possible while 255 will be lightest possible. Our goal is to create a deep learning model that will predict which digit it is . Here 28 x 28 pixels grid are flattened to 784 features for each

Another post starts with you beautiful people! Hope you have learnt the core concepts of Deep Learning from my  previous post . If not please visit once because it is required before creating our first keras model.  Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. Keras workflow has following four steps- Specify the architecture, Compile the model, Fit the model, Predict. Let's understand how we can achieve each steps- Specify the architecture:- In the first step you define the architecture of your model like- how many layers do you want? how many nodes in each layer? what activation function do you want to use? Compile the model:- This step specifies the loss function and some details about optimization. Fit the model:- This step is the cycle of Backpropagation and model optimization of model weights with your data. Predict:-  In this last step you use your model to make predictions. Now we wi

Another post starts with you beautiful people! From this post I am going to share my learning from the data camp  and various sources about the Deep Learning- a subfield of machine learning inspired by the structure and function of the brain (called artificial neural networks). Before jumping into the Python code, we must understand nuts and bolts of Deep Learning. That is what we are going to learn in this post. When you hear the term Deep Learning, just think of a large deep neural network. This network is so much powerful is that Deep Learning gives amazing results for text, images, audio and video data. For every problem, deep learning models capture interactions and how they capture the interactions we need to understand following three components- Input Layer :- situated in far left side in neural network and represents our predictive features. Output Layer :- situated in far right side and represents the prediction from our model Hidden Layer :- all layers that are n

A new post starts with you beautiful people and a very Happy New Year to all ! It was quite a fantastic last year with respect to learning many new things in Data Science and I was very happy to see that many aspiring data scientists like you had contacted me through my  facebook page . It was an honor for me that I was able to solve your queries and motivated many of you! This year also I will continue my posts about my learning and will share with you all so don't stop, stay positive, keep practicing and try again and again :) In this post I am going to share nuts and bolts of handling a natural language processing (NLP) task which I had learnt while I was working for a Singapore client. In that project I scraped the different e-commerce merchants' product related data through the apis, web scraping and then I performed text cleaning before applying a machine learning algorithm to classify the product categories. Such kind of task you may encounter in your life. So let&