Python for Data Science and Machine Leaning

Number of Hours : 30 Hours

Artificial Intelligence (AI) has emerged as one of the decisive expertise with applications across various industry domains. Machine Learning (ML), a subset of AI, is an important set of algorithms used for solving several business and social problems. Companies across different industry sectors such as retail, finance, insurance, manufacturing, health-care are planning to build and offer AI based solutions to stay competitive in the market

Prerequisites:

Basic Knowledge of Data Science

Courses Objectives:

After the course, you will be able to:

    • Implement Regression Models
    • Implement Clustering Techniques
    • Forecast using Time Series Algorithms
    • Implement Text Analytics
    • Mean and Variance analysis
    • Probability Distributions
    • Hypothesis Testing
    • Building Simple Linear Regression Model
    • Creating Feature Set(X) and Outcome Variable(Y)
    • Splitting the dataset into training and validation sets
    • Fitting the Model
    • Model Diagnostics
    • Residual Analysis
    • Outlier Analysis
    • Making prediction using the model
    • Multiple Linear Regression
    • Building the model
    • Multi-Collinearity
    • Making prediction using the Multiple Linear Regression model
    • Classification Overview
    • Encoding Categorical Features
    • Building Logistic Regression Model
    • Model Diagnostics
    • Predicting on Test Data
    • Creating a Confusion Matrix
    • Measuring Accuracies
    • ROC & AUC
    • Gain Chart and Lift Chart
    • Decision Trees
    • Building Decision Tree classifier using Gini Criteria
    • Building Decision Tree using Entropy Criteria
    • Developing a Gradient Descent Algorithm for Linear Regression Model
    • Scikit-learn Library for Machine Learning
    • Advanced Regression Models
    • Random Forest
    • Boosting
    • Concept of Clustering
    • K-means Clustering
    • Hierarchical clustering
    • Forecasting using Moving Average
    • Decomposing Time Series
    • Auto Regressive Integrated Moving Average Models (ARIMA)
    • Sentiment Classification
    • Text Pre processing
    • Naive Bayes Model for Sentiment Classification
    • Using N-grams