Data Science Statistics: Using Python to Compute & Visualize Statistics


Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level



Overview/Description

Learners continue their exploration of data science in this 10-video course, which deals with using NumPy, Pandas, and SciPy libraries to perform various statistical summary operations on real data sets. This beginner-level course assumes some prior experience with Python programming and an understanding of basic statistical concepts such as mean, standard deviation, and correlation. The course opens by exploring different ways to visualize data by using the Matplotlib library, including univariate and bivariate distributions. Next, you will move to computing descriptor statistics for distributions, such as variance and standard error, by using the NumPy, Pandas, and SciPy libraries. Learn about the concept of the z-score, in which every value in a distribution is expressed in terms of the number of standard deviations from the mean value. Then cover the computation of the z-score for a series using SciPy. In the closing exercise, you will make use of the matplotlib data visualization library through three points represented by given coordinates, then enumerate all of the details which are conveyed in a Boxplot.



Expected Duration (hours)
1.3

Lesson Objectives

Data Science Statistics: Using Python to Compute & Visualize Statistics

  • Course Overview
  • create and configure simple graphs with lines and markers using the Matplotlib data visualization library
  • use the NumPy library to manipulate arrays and the Pandas library to load and analyze a dataset
  • generate histograms and pie charts to analyze distributions and create scatter plots to plot the relationship between two variables in a dataset
  • apply Python native functions such as max() and sum() to summarize distributions and visualize these values using Matplotlib
  • use NumPy to compute statistics such as the mean and median on your data
  • calculate statistics such as the mode and standard error of mean using the SciPy library and compute more statistics such as variance and values at various percentiles using NumPy
  • use NumPy to compute the correlation and covariance of two distributions and visualize their relationship with scatterplots
  • standardize a distribution to express its values as z-scores and use Pandas to generate a correlation and covariance matrix for your dataset
  • create and configure a graph using Matplotlib, enumerate the details conveyed in a Boxplot, compute statistical values using the NumPy function, and compute the correlations between all pairs of columns in a Pandas dataframe
  • Course Number:
    it_dssds2dj_01_enus

    Expertise Level
    Beginner