Mastering Applied Data Analytics with Python

Install and configure Python, Anaconda, and Jupyter Notebook to set up a browser-based Python environment for deep learning work, including verifying versions and launching notebooks.

Create and manipulate NumPy arrays in a Jupyter notebook using Python, compute min, max, and axis sums, and troubleshoot multi-dimensional array declarations.

Explore how to generate two-column random data, build a numpy histogram, and compute column correlations in a jupyter notebook, with seed control and section-wise execution.

Create and explore NumPy arrays, examining shape, dtype, and dimensions, then perform basic array operations and type conversions within Python for data analytics.

Create a Python Jupyter notebook to explore linear optimization by building a 2d array, using numpy for linear algebra, and solving ax=b with numpy's solver.

Analyze a csv file with pandas in a Jupyter notebook, read the csv data, create series, and perform data analytics on attributes like name, age, career, province, and sex.

Load a csv with pandas read_csv, inspect the dataframe with head and tail, compute sums and descriptive statistics with describe, and explore index and data types.

Explore how to create histograms in Python using NumPy and Matplotlib, building mu and sigma based histograms in a Jupyter notebook, adjusting bins and styles, and saving the figure.

Create a demo time series by importing matplotlib, numpy, and pandas; generate a random series with pd.series, plot with style Co and alpha 0.4, and save as series.png.

Create and compare multiple subplots in matplotlib, using 2 to 1, 2 to 2, 2 to 3, and 2 to 4 layouts with line and scatter plots, saving the figure.

Master pandas for data analysis by installing and importing the library, then load and explore CSV, Excel, and JSON data in a Jupyter notebook, using read_csv, read_excel, read_json, and df.head.

Apply multiple filter criteria in pandas to a Zillow dataset by reading CSV with read_table, filtering by value, state, or metro using is in, and preparing data for downstream tasks.

Change data types in pandas by inspecting dtypes, converting a column to float, parsing dates to datetime, and reading csv with dtype hints, preparing for filtering rows.

Filter rows in a pandas dataframe by column values such as state, metro, and region id/name, apply price thresholds, preview with head, and prepare for selecting multiple rows and columns.

Mastering the selection of multiple rows and columns in pandas data frames, using iloc and loc, with practical examples of indexing, head outputs, and preparing for sorting operations.

Learn to sort pandas data frames and series by single and multiple keys, including ascending and descending orders, and inspect the head values to view top rows.

Explore the movie.csv dataset in a case study, inspect parameters like director and gross, and convert the file into a pandas data frame in a Jupyter notebook.

Dissect the anatomy of a movie dataset by loading a csv into a pandas dataframe, inspecting its shape (4916 by 28), and viewing head and tail values.

Explore accessing the main data frame components in a movie dataset using pandas, including columns, index, and data, and learn how to print and inspect their types and values.

Examine data types in a movie dataset using Python, employing dtypes and get dtype counts to reveal 28 columns, including 13 float attributes, 3 integer attributes, and 12 object attributes.

select a single column as a series from a movie data set, inspect its type, convert to a dataframe, and combine director and gross for analysis.

Create and call series methods to build data sets, check length and shape, and use head, value counts, describe, is null, fill, and drop.

Apply operators on a series to IMDb score with plus one, times 2.5, and modulus, then verify boolean comparisons and director data for James Cameron.

Learn to chain series methods to filter and summarize data, create subsets like actor one Facebook likes or directors, and apply value_counts, is null checks, and type analysis.

Make an index meaningful by creating datasets, applying set index and reset index with movie title, and querying for insights as OpenCV's face and image recognition are introduced.

Install OpenCV for Python via pip and build a face recognition module using computer vision for image analysis and authentication.

Learn to build a face recognition pipeline in Python with OpenCV by preparing training data, labeling faces, and detecting faces using a cascade classifier.

Define a training data pipeline that reads subject folders, builds labeled faces, detects faces, and prepares data for predicting phases in images.

Prepare training data by pairing faces with labels, print the data and counts, then create LPB and Fisher face recognizers to predict and draw rectangles around faces.

Create and train a face recognizer using OpenCV, predict on test images, draw rectangles and labels, and display results to validate recognition of celebrities.

Calculate boolean statistics on the movie csv dataset using Pandas and NumPy, identifying films longer than two hours and summarizing with sum, mean, value counts, and describe.

Construct and combine multiple boolean conditions to filter data, using criteria for IMDb score, content rating, and title and year values, then evaluate the final boolean index.

Learn to filter data with boolean indexing using multiple criteria on movie data, including IMDb score, content rating, and title year.

Replicate boolean indexing with index selection on college data set in Python by converting a CSV to a dataframe, setting index by state and filtering Texas, California, and New York.

Explore creating and evaluating sorted and unique indexes on college data, test monotonicity, measure timing with timeit, and resolve index errors while querying with specific locations like Stanford University.

Analyze stock prices by loading a csv with date, open, high, low, close, and volume; build a time series, compute descriptive statistics, and visualize close price trends with bounds.

Translate SQL where clauses into pandas filters to query the employee dataset in a Jupyter notebook, filtering by department in, gender female, and base salary between 8000 and 12000.

Analyze the normality of stock market returns using Amazon stock data in a csv, computing daily returns, histogram with bins, mean, standard deviation, and absolute z-scores.

Improve readability of boolean indexing with the query method in Python data analytics, covering department and gender filters, selecting columns, and base salary between 8,000 and 12,000.

Preserve the movie data series by applying the where method in pandas, compute describe statistics for Facebook likes, and visualize with a histogram to interpret the dataset.