Object detection has become a major part of the machine learning models. So I build a model using CNN which stands for convolution neural networks. I used Haar cascade classifier for extracting the faces from the images. For female I used label 0 and for male 1. For training model I used google image as source and downloaded random images.

Developed a deep learning model to achieve near state of the art performance on the MNIST handwritten digit recognition task in Python using ‘Keras’ deep learning library. Images of digit were taken from variety of scanned documents, normalized and centered. Each image is 28x28 pixel square and total 60,000 images were taken to train the model.

Created a chatbot with the help of ‘nltk’ library. In our dataset we have some queries and based on that their respective answers. We have some numerical values also like age, working days. As for creating chatbot I have gone through Count Vectorization transformation for Bag of Words and tfidf Vectorization transformation for Term Frequency-Inverse Documents Frequency. I used cosine similarity for pair of vectors.

Our dataset contains the sample of candidates of a company who is facing challenge that about 30% of the candidate who accept the job offers but do not join the company. So with the help of Decision Tree algorithm, ‘gini’ as criterion, I build a model to predict the likelihood of candidate joining the company.

This project deals with the Time to Failure and Predicting which equipment of machine is likely fail. Our dataset which is previous data consist of 3 settings, 21 sensors, id and cycle. Now on the basis of dataset, to figure out the important feature which plays the role in failure of machine, I applied Feature Engineering as Backward Elimination. After getting necessary feature I applied OLS method. Hence to get better result and for more accuracy of prediction I applied Random Forest algorithm of Machine Learning, then finally plotted and concluded the result.

This project deals about the analysis of parameter in which Weather is dependent. There are various visualization we had perform in which we shown the drastic change of weather on the basis of wind. We had also done some prediction on the basis of data to predict the cities or town where there are some possibilities of raining or sunny weather. Basically our data was live data, it changes at every instance of weather change, so that was a challenging phase for us to store and analyze.

Extracting data from websites and read csv file or excel file in python Jupyter Notebook, reading and analysis or files, some assumptions, looking for NAN values, describe, info, mean, median, mode and then deal with NAN values. After that dataframe will be created and then perform visualization and conclude some productive or useful conclusion.