Machinelearning Python

This repository contains Machine Learning Concepts/Analysis and Algorithms examples.

Table of Contents

• Analysis

  • Analysis-Titanic Dataset
  • Analysis-IRIS Dataset
  • Analysis-HousePrice Dataset

• Data Wrangling

  • Understanding Dataset
  • Pandas Read From URL
  • Data Consolidation
  • Pandas Profiling
  • MySQL and Pandas
  • Pivot Tables and GroupBy

• Data Visualization

• Feature Engineering

• ML Concepts

  • PerformanceMeasure-Classification
  • Bias-Variance TradeOff
  • Curse-Of-Dimentionality

• ML Algorithms

  • Decision Trees
  • Support Vector Machines
  • K-Means Clustering
  • FP-Growth
  • Gausian Naive Bayes
  • Simple Linear Regression
  • Polynomial Linear Regression
  • KNN
  • Logistic Regression

• Analysis on Titanic Dataset

  This example is analysis on Titanic Dataset. [source Code]

  • Load the data[titanic.csv]
  • Clean and Prepare Data
  • Create Sparse Matrix
  • Split Dataframe as: Representation of Split:
  • Apply ML Model
  • Make Prediction
  • Cross Validate
  • Make Predictions

• Analysis on IRIS Dataset

  This example is analysis on IRIS Dataset. [source Code]

  • Load the data[iris.csv]
  • Clean and Prepare Data
  • Split Dataframe as above for Pictorial representation
  • Apply ML Model
  • Make Prediction
  • Cross Validate
  • Make Predictions

• Analysis on House Price Dataset

  This example is analysis on House Price Dataset.[Source Code]

  • Load the data[HousePricingTutorial.csv]
  • Normalize
  • Analyse Correlation
  • Clean and Prepare Data
  • Split Dataframe as above for Pictorial representation
  • Apply ML Model
  • Make Prediction
  • Cross Validate Refer above for Pictorial representation
  • Make Predictions

• Understanding Dataset

  This example explains basic computing options with Pandas Dataframe/Series [Source Code]

  • Load the data[Loan.csv]
  • Undersatnding Types
  • Column Operations
  • Row Operations

• Pandas Read From URL

  This example explains how we can access data present on Cloud(Azure Cloud Storage). [Source Code]

  • Storing Data on Cloud (Azure Cloud Storage).
  • Accessing the Data using Pandas Library.

• Data Consolidation

  This example explains various methods of consolidating Data. [Source Code]

  • Concatinating Dataframe
  • Appending Dataframe
  • Joining Dataframe
  • Merging Dataframe

• Pandas Profiling

  This example explains how to do Data Profiling using pandas-profiling library. [Source Code]

  • Load the Data [iris.csv]
  • Apply profiling
  • Save the ouput in html

• MySQL and Pandas

  This example explains the connectivity between MySQL and Pandas. [Source Code]

• Pivot Tables

  This example explains the concept of Pivot Tables and GroupBy. [Source Code]

  • Load the data[schools_with_btoilet.csv/schools_with_gtoilet.csv]
  • Apply Panda's Pivot Method

• Data Visualization

  This example explains how to Visualize data in various forms of Graphs. [Source Code]

  • Pair Plot
  • Line Graph
  • Histo Graph
  • Bar Plot
  • Scatter Plots
  • Box Plots
  • Heat Maps

  ---

• Feature Engineering

  This example explains common methods used for Feature Engineering. [Source Code]

  • Load the data[mercedesbenz.csv]
  • Nominal Encoding (One-Hot Normal | One-Hot KDD | Count/Frequncy)
  • Ordinal Encoding (System | Custom)

  ---

• Performance Measure for Classification

  This example explains Concepts like Confusion Matrix | Accuracy | Precision | Recall | F1-Score. [Source Code]

  • Understanding Confusion Matrix
  • Understanding Accuracy
  • Understanding Precision
  • Understanding Recall
  • Understanding F1-Score

  ---

• Bias-Variance TradeOff

  This Sheet explains the concept of Bias-Variance TradeOff.

  ---

• Curse-Of-Dimentionality

  This Sheet explains the concept of Curse Of Dimentionality.

  ---

• Decision Trees

  This example explains Decison Trees' theory with an implementation in Python. [Source Code]

  • Load the data[IRIS.csv]
  • Decision Trees Classification using GINI Index
  • Decision Trees Classification using Information Gain
  • Visualizing Decision Trees
  • Decision Trees Regression

  ---

• Support Vector Machines

  This example explains Decison Trees' basic theory with an implementation in Python. [Source Code]

  • Load the data[IRIS.csv]
  • Computing SVM

  ---

• K-Means Clustering

  This example explains K-Means Clustering basic theory with an implementation in Python. [Source Code]

  • Load the data[IRIS.csv]
  • Computing K-Means Clustering
  • Determining K - Elbow Method | Silhouette Method
  • Mini-Batch K-Means

  ---

• FP-Growth

  This example explains FP-Growth basic theory with an implementation in Python. [Source Code]

  • Install pyfpgrowth [pip install pyfpgrowth]
  • Prepare Dummy Data
  • Computing FP-Growth

  ---

• Gausian Naive Bayes

  This example explains Gaussian Naive Bayes basic theory with an implementation in Python. [Source Code]

  • Load the data[IRIS.csv]
  • Computing Gaussian Naive Bayes using scikit-learn
  • Computing Gaussian Naive Bayes by logic

  ---

• Simple Linear Regression

  This example explains Simple Linear Regression's basic theory with an implementation in Python. [Source Code]

  • Load the data[SimpleLinearRegression.csv]
  • Computing Simple Linear Regression by logic
  • Computing Simple Linear Regression using Scikit-learn

  ---

• Polynomial Linear Regression

  This example explains Polynomial Linear Regression's implementation in Python. [Source Code]

  • Load the data[DatasetForSimpleAndPolynomialLinearRegression.csv]
  • Computing Simple Linear Regression using Scikit-learn
  • Computing Polynomial Linear Regression
  • Comparision of different Polynomial Linear Regression graphs based on different degrees.

  ---

• KNN

  This example explains KNN Algorithm and its implementation in Python. [Source Code]

  • Load the data[IRIS.csv]
  • Compute KNN
  • Compute KNN on different values of K

  ---

• Logistic Regression

  This example explains concepts of Logistic Regression Algorithm and its implementation in Python. [Source Code]

  • Load the data[IRIS.csv]
  • Compute Logistic Regression

  ---