Data-Science

Complete Reference Guide to "Python for Data Science". This repository is a Statistics and Machine Learning Cookbook, providing Hands On Coding overview with Python and popular libraries like Pandas, Numpy, Matplotlib, Seaborn, sk-learn, scipy, stats, statsmodels to name a few. It covers various Machine Learning Models, Exploratory Data Analysis Techniques and End to End Projects that can help you refresh your Data Science skills.

Topics Covered:

Exploratory Data Analysis (EDA):

1)  Descriptive Statistics
2)  Inferential Statistics
3)  Missing / Null Value Check and Treatment
4)  Outlier Treatment
5)  Redundant / Zero Variance Column Treatment
6)  Encoding Categorical Variables to numeric
7)  Multicollinearity and Correlation Treatment / Dropping of Twin Variables
8)  Feature Engineering
9)  Feature Scaling and Standardization
10) Sentiment Analysis and Web-Scraping

Machine Learning Models:

1)  Supervised Machine Learning

    I)  Classification (Binary and Multiclass)

        a)  Decision Tree Classifier
        b)  Random Forest Classifier
        c)  XG Boost
        d)  Support Vector Machines Classifier
        e)  Logistic Regression Classifier
        f)  Naïve Bayes Classifier
        g)  K-Nearest Neighbor CLassifier
        h)  Stacking Classifier
        i)  Local Outlier Factor
        j)  Isolation Forest

    II) Regression

        a)  Linear Regression
        b)  Ridge Regression (L1)
        c)  Lasso Regression (L2)
        d)  Elastic Net Regression (Combination of L1 and L2)
        e)  Decision Tree Regressor
        f)  Random Forest Regressor
        g)  Support Vector Regressor

2)  Unsupervised Machine Learning

        I)  Clustering

            a)  K-Means Clustering

Finally, you will find some Machine Learning Projects from Data Acquisition to Model Building and Evaluation to give you a holistic view of the entire workflow.