The Ultimate Data Science (Python & R) Course: All In One

Learn the fundamentals of Jupyter basics, including executing code cells with shift enter, inserting and moving cells, and handling kernel interruptions with stop, restart, and clear output.

Learn to load and analyze data with Python pandas, using auto LPG dataset (1970–1982) to read, sort by fuel efficiency, extract makes from names, clean duplicates, and group by makes.

Visualize fuel efficiency trends from the 1970s using the bouquet interactive visualization library, with interactive scatterplots, hover details, and widgets to zoom and color by Ford, Volkswagen, and Honda.

Learn to load and split data, train linear regression and random forest models with scikit-learn, evaluate predictions against test data, and create interactive visualizations of deltas using pandas.

Discover how data science blends statistics, processing, machine learning, and visualization to extract insights, using open source tools and Python with Anaconda for collaborative production analytics.

Enable cross-functional collaboration in open data science by uniting statisticians, researchers, computational scientists, developers, and DevOps to move analytics from exploration to production with Anaconda.

Explore, model, predict, share, and deploy in the modern data science development workflow, from data exploration to production deployment and collaboration across teams.

Import pandas as pd, inspect data with describe and info, and review memory usage and data types. Visualize year vs fuel efficiency with Map Plot Lib in Jupyter.

Enrich data in pandas by in-place replacing origin codes with american, european, and asian, and derive make and model from vehicle names using split and list comprehension.

Explore boolean masks and indexing in pandas to filter, update, and visualize data frames by origin, cylinders, and names, using interactive, open data science techniques.

Learn to read a csv with pandas, load a 40,000-row, 83-column fuel economy data frame, and select columns via a colon and a column list.

Learn to subset and reorder a dataframe to focus on key fields, convert select columns to category types for memory efficiency, and apply masks and contains for filtering.

Learn how to group data with pandas by the fields make and model, explore the resulting groups, and visualize fuel efficiency trends across years with custom plotting.

Connect to a SQLite database using pandas read_sql, exploring the Chinook database to pull tracks and related tables via joins, and consolidate data into a normalized dataframe.

connect to a database and normalize data in pandas by renaming columns, then use SQL-like queries and Python counters to analyze track metadata and composer counts.

Explore time series data using sqlite and pandas, parse invoice dates, index by invoice id, group by year and month, and plot the month-end total.

Learn to read and write Excel files with pandas, using read_excel and to_excel, specify sheets, and export multi-sheet workbooks with ExcelWriter and xlsxwriter for data from SQL databases.

Save your notebook and publish it to Anaconda Cloud's analytics artifact repository by signing into Anaconda Cloud or Anaconda Enterprise account and using the upload button in the Jupiter window.

Explore the open data science ecosystem with the Anaconda platform, highlighting cross-platform distribution, hundreds of precompiled packages, and conda-based reproducible data workflows for Python and R.

Discover conda and the anaconda distribution, offering language- and platform-independent packages, dependency management, and reproducible environments through channels like conda forge, plus the capsule capability.

Explore how the Anaconda platform layers—from distribution to enterprise notebooks and Mosaic—enable collaborative, reproducible analytics across desktops, data labs, and production clusters.

Explore how the Anaconda desk library enables parallel data processing with task graphs on single or distributed machines, supporting terabyte-scale datasets and interactive visualizations with the book and data shader ecosystems.

Navigate data science workflows with the Anaconda platform, moving from single-machine analysis to collaboration, publish notebooks and environments to the artifact repository, and deploy reproducible models at scale.

Create a new project and invite teammates to collaborate in a centralized, secure environment. Work with per-project Conda environments and notebooks, and publish to the Anaconda Enterprise repository.

Learn to build high quality, interactive visualizations with the book data visualization library that uses grammar for graphics, requires no JavaScript, and renders via JSON in modern browsers.

Learn to plot pandas dataframes with bokeh charts, creating interactive histograms, scatterplots, bar charts, and heat maps using iris flowers and auto mpg datasets with petal length, petal width, displacement.

Learn to build high quality interactive visualizations with the book plotting library, creating figures and glyphs, and using a column data source to render per-point attributes as JSON.

Learn to manage plot construction in Bokeh using a column data source. Map species to colors, apply a hover tool, and render interactive visualizations from the iris data set.

Learn to add widgets to modify interactive Bokeh plots, link multiple figures with shared axes, arrange them in a grid, and enable linked brushing and tooltips.

Learn to build multi-dimensional interactive visualizations with widgets in Jupyter, linking plots via interactivity tools, updating data sources with NumPy, Python widgets, and custom JavaScript callbacks.

learn to generate standalone interactive web plots from bokeh by saving to static html files for web server assets, enabling client-side interactivity with hover tools and pan/zoom.

Learn to build data ops with a Python script server, render interactive plots including histograms from static and streaming data, and deploy via a web app and iframe.

Explore hollow views for composing interactive visualizations on top of bokeh. Optimize package management in an Anaconda environment by comparing conda and pip installations.

Learn to add channels in Navigator, including the r channel, to access conda’s large package ecosystem and install the essentials meta package with its dependencies.

Learn how to upgrade, downgrade, and remove packages in navigator using three example packages—book, dusk, and xarray—by selecting versions, applying changes, and managing downloads, package cache, and linking.

Create and switch conda environments in Anaconda Navigator. Start with a minimal python 3.5 core, then add the Anaconda meta package and leverage package cache with linking to save space.

Explore how to manage conda environments and Jupyter kernels, verify Python versions, switch kernels, and understand how Anaconda isolates packages to keep system Python safe.

Master conda from the command line across Windows, macOS, and Linux, enabling environment activation and package installation. Explore info, list, and channels to manage environments efficiently.

Master conda environment management, remove the base and dependent packages, create a Python 3.5 notebook with pandas and seaborn, and switch kernels in Jupyter.

Explain the differences between pip and conda, and explore continuum curated, community curated channels, and how to use pip within conda environments.

Install Peewee via pip in a conda environment and verify the correct kernel in the Jupyter notebook. Define Peewee models for person and pet, create sqlite tables, and run queries.

Conda and pip updates are essential for your data science workflow; learn how to update conda in the root environment and update pip per Python interpreter.

Learn how conda environments provide reproducible, encapsulated open data science work, and how to share them via YAML exports and Anaconda Navigator.

Learn to search for and install conda packages on Anaconda Cloud, focusing on Blaze and Data Shape across channels, using Navigator or conda, and manage channels for reproducible data science.

Learn to manage conda environments, install essentials and dev tools, and set up python and r data processing tooling for AR-enabled data visualization and notebook workflows.

Explore accessing and processing data with dplyr and tidyr, using the nyc flights dataset to arrange by carrier, origin, destination, and select key columns.

Chain select, arrange, group by, and summarize to compute mean delays by carrier; filter origin and destination; reshape data with gather and spread for tidy tables.

Learn to build visualizations with ggplot grammar by mapping carat to x and price to y, layering with geom_point, and exploring color, alpha, and log scales for the diamonds dataset.

Learn to refine ggplot visualizations by adjusting alpha and size, using facet wrap to split data, and interpreting trends with linear estimators and confidence intervals across diamonds and iris examples.

Build linear predictive models with the diamonds dataset for predictive analytics, split data into training and testing sets, fit price to carat and cut, and compare observed versus predicted plots.

Learn to build and compare linear predictive models using the LM framework, train with data, and visualize the fit to analyze model predictions in predictive analytics.

Learn to create interactive visualizations in R using bouquet plots and Shiny apps, leveraging the book and shiny packages to explore linear models, histograms with density overlays, and iris clustering.

Bridge Python and R using the RPI two module in Jupyter, using magics like percent R to pass data and build regression with a pandas data frame.

Install or update the necessary packages, then build a supervised learning model using linear regression to predict fuel efficiency, splitting data into training and testing sets.

Generate predictions from a trained predictive model, evaluate accuracy on a test set, and compare linear regression with classifiers like random forest, achieving 87% car origin accuracy.

score and evaluate linear regression models using 10-fold cross-validation, comparing training and test accuracy and mean squared error to gauge model quality and the benefits of parallel evaluation.

Visualize model performance with a scatterplot of actual fuel efficiency versus predicted values and a support vector machine classifier decision threshold to illustrate classifier behavior.

Anaconda Fusion connects Excel spreadsheets and the open data science world through Jupyter Notebooks, enabling analysts and data scientists to collaborate by accessing routines and algorithms from Excel.

Learn how to install and start Anaconda Fusion on Mac or Windows (Excel 2016+), configure the Fusion channel and environment, then connect Excel to the Fusion server for notebook workflows.

Connect a spreadsheet to a Fusion code sheet and run a transaction inspector to visualize sales data. Explore categories and entries to see how code sheets process datasets with Fusion.

Access distributed data across formats—from text files to HDFS—using Mosaic, build synthetic views with data connectors and APIs, and explore and visualize joined data in the data browser.

Learn how to install mosaic with Anaconda Enterprise, obtain a license, and launch it from the command line or the Anaconda Navigator app panel via the cloud channel.

Install mosaic via the Anaconda Mosaic channel, create a conda environment, start a web server, register data sources, and build data views that export to pandas data frames for Jupyter.