Python Programming with AI for Business Intelligence

Set up your Python coding environment in Jupyter notebook for data analysis and write your first hello world using the print function, then run the cell to see output.

Master Python variables and naming conventions, including assignment operator and data types like strings and numbers. Use descriptive, case-sensitive names, avoid starting with digits or keywords, and use underscores.

Explore python data types including integers, float, string, and boolean, with practical examples that show how each type dictates operations, calculations, and data handling.

Learn to convert data types in Python with int, float, and str, and apply type casting to turn strings into numbers for data analysis.

Master Python arithmetic operators, including plus, minus, multiplication, division, modulus, and exponential. See hands-on examples that add numbers, compute remainders, and demonstrate exponentiation and squaring.

Learn Python comparison operators, greater than, less than, greater than or equal to, less than or equal to, equals, and not equal, and how they yield boolean true or false.

Explore how python logical operators and, or, and not combine conditional results to produce boolean outputs, with practical examples using greater than and less than comparisons.

Explore how to create lists in Python with brackets, including strings, numbers, booleans, and mixed data types, and practice indexing, slicing, and modifying with append, insert, and remove.

Learn Python sets and perform operations like union, finding common values, difference, and element modification. Practice adding, removing, and multiplying set elements through iteration.

Explore Python dictionaries as key-value pair collections, using keys, values, and items methods to access, modify, and extend entries such as name, age, city, and email.

Explore python conditional statements by using if, elif, and else to evaluate conditions, print results, and handle true or false outcomes in simple data checks.

Explore how to use logical expressions with conditional statements in Python to classify ages, temperatures, and graduation status, demonstrating and applying or not operators to produce automated results.

Master Python looping structures with for loops to iterate over lists and print each item, and while loops to repeat until a condition is met, including filtering even numbers.

Define, create, and call a custom Python function using def to compute category percentages from total respondents, then test with male and female values.

Load an Excel dataset into a pandas dataframe in a Jupyter notebook. Install and import pandas, then use read_excel and head to preview the data.

Impute missing values in a dataframe using Python and scikit-learn's simple imputer, applying median for numeric data and most frequent for categorical data.

Discover how to detect and correct inconsistent values to assign proper numeric data types in Python, using pandas df.dtypes and code to identify non-numeric costs and convert them to float.

Clean data by removing rows with inconsistent values in a numeric column using pandas. Then assign correct types, float for cost and date time 64 for date, with code examples.

identify and remove duplicate rows in a dataset using Python and pandas drop_duplicates, creating a clean data frame and exploring the duplicate detection workflow with ChatGPT generated code.

Learn to manipulate data by sorting numeric values with Python and pandas, generating ascending or descending insights. Compare costs across categories like games, books, and others to reveal business intelligence.

Learn to filter a data frame with Python by country and product category, extracting data for France and games, and removing France from the dataset.

learn how to merge extra variables into an existing cleaned dataset by loading a second dataset containing refund, and merging on the common order id to add the refund column.

learn how to concatenate extra data to an existing dataframe by row using pandas pd.concat, load the extra data, and build a final dataframe for business intelligence.

Explore exploratory data analysis on sales data to uncover insights, guide decisions, and prepare effective models for business intelligence. Answer key questions about country trends and profitable customers.

Apply frequency analysis to identify the country of residence with the highest customer counts, using pandas value_counts and a bar chart plotted with matplotlib in a Jupyter notebook.

Learn to perform descriptive analysis on numeric variables in Python, focusing on order value, cost, and refund, using describe to report mean, median, standard deviation, and percentiles.

Identify the top three product categories by median order value and median cost using the group by method in Python.

Analyze the most loyal customers of your superstore using pivot tables in Python and ChatGPT. Combine repeat purchase frequency, median order value, and median cost to identify top customers.

Analyze cross-tabulations of sales manager and product category with pandas crosstab and heatmaps, using group by and pivot tables to identify which manager drives sales most across categories.

Apply correlation analysis to three numeric variables—order value, cost, and refund—to compute and visualize a correlation matrix and heatmap, revealing strong positive relationships.

Explore inferential data analysis through hypothesis testing, distinguishing null and alternative hypotheses, and learn how to infer population characteristics from a sample using data collection, analysis, and interpretation.

Explore confidence level, significance level, and p-value in hypothesis testing, with practical examples showing how to decide between null and alternative hypotheses using a 5% significance threshold.

Explore the steps of hypothesis testing, from null and alternative hypotheses to significance level, normal distribution checks, and one-way ANOVA, comparing exam scores under new versus traditional teaching methods.

Assess whether numeric variables follow a normal distribution and apply transformation methods if not, to improve normality for analysis. Focus on order value, costs of goods sold, and refund amounts.

apply square root transformation to numeric variables to improve normality, using numpy sqrt and plots, evaluating order value, cost, and refund, with refunds needing other transformations later.

Apply logarithmic transformation to three numeric variables, order value euro, cost, and refund, in Python, assess shifts toward normal distribution, compare with square root results, and note Box-Cox coming next.

In this lesson, apply the Box-cox transformation in Python to order value, cost, and refund, compare with square root and logarithmic transforms, and prepare for the Johnson method.

Apply the Johnson transformation to three numeric variables, compare with Box-Cox, and decide transformations: Box-Cox for order values, Johnson for cost, and none for refund.

Use one way Anova to assess differences in the cost of goods sold across pc, mobile, and tablet devices at a 0.05 significance level, interpreting f statistic and p value.

Demonstrates a Pearson correlation test on box-cox transformed order value and cost with refund, testing significance at 0.05 and showing all pairwise relationships as significant.

Apply regression analysis to measure the impact of order value and cost on refund, test hypotheses at 0.05, and interpret coefficients, p-values, and r-squared.