This repo contains the exercises made for the course of Jose Portilla on Udemy.
The course teaches how to use NumPy, Pandas, Seaborn , Matplotlib , Plotly , Scikit-Learn , Machine Learning models, Tensorflow, Deep Neural Networks and more.
The exercises offer the possibility to reproduce the real analysis process using real data (like datasets on Kaggle) or fake data (created for the scope of the course).
-
911 Calls Data Capstone Project .ipynb : Analysis of the Kaggle 911 Dataset with visualizations in Seaborn and Matplotlib.
-
Choropleth Maps Exercise .ipynb: choropleth maps with Plotly.
-
Decision Trees and Random Forest Project .ipynb: Analysis of a dataset from LendingClub.com with visualizations in Seaborn and Matplotlib and Machine Learning models with Scikit-Learn.
-
Ecommerce Purchases Exercise .ipynb: analysis of a dataset with fake Amazon data with Pandas.
-
K Nearest Neighbors Project .ipynb: using Numpy, Maplotlib, Pandas, Seaborn to analyze a dataset and the applying the KNN model to the data using Scikit-Learn.
-
Linear Regression - Project Exercise .ipynb: using Numpy, Maplotlib, Pandas, Seaborn to analyze a dataset about Ecommerce customers and the applying the Linear Regression model to the data using Scikit-Learn.
-
Logistic Regression Project .ipynb: using Numpy, Maplotlib, Pandas, Seaborn to work with a fake advertising data set, indicating whether or not a particular internet user clicked on an Advertisement. Cresating a Logistic Regression model with Scikit-Learn to predict whether or not the users will click on an ad based off the features of the users.
-
NLP Project .ipynb: Classify Yelp Reviews into 1 star or 5 star categories based off the text content in the reviews. The analysis has been done using the Yelp Review Data Set from Kaggle.
-
SF Salaries Exercise .ipynb: simple Pandas analysis using the SF Salaries datased from Kaggle.
-
Support Vector Machines Project .ipynb: SVM application with Scikit-Learn on the Iris dataset.
-
Tensorflow Project Exercise .ipynb: Tensorflow application on the UCI dataset - created a Deep Neural Network using the contrib.learn module.