Combine what you've learned so far to analyze a real-world case from start to finish.

Machine Learning with Python Libraries

In this module, we'll work on an industry-level machine learning project based on predicting weekly retail sales with different given factors.  We’ll learn the most efficient techniques used to train and evaluate scalable machine learning models. After completing this module, we’ll be able to take on industry-level machine learning projects, from data analysis to creating efficient models and providing results and insights. 

The code for this module is built around the TensorFlow framework, which is one of the premier frameworks for industry machine learning, and the Python pandas library for data analysis. This module requires basic knowledge of Python and TensorFlow as its prerequisites. By the end of this module, we’ll have hands-on experience in creating machine learning projects.

TensorFlow

## Chapter Goals:
- Learn about the retail dataset used in this case study
- Read the separate data files that comprise the dataset


## A. Starting off the project

Let's say you're a machine learning engineer at a large retail corporation, and your supervisor just gave you this dataset and said,

*"I want a system that can make future sales predictions for these 45 stores. We want to know whether they'll make enough money to justify keeping them. Here's a dataset containing the past sales of these stores."*

This is a pretty short and vague description of the project, which is normally the type of description you'd get from a manager or supervisor. Luckily, we can learn more about the project by looking through the dataset.

Industry data usually comes in CSV files, XLSX spreadsheets, JSON data files, or can be accessed from a database using SQL. In this case, our dataset comes in three CSV files: *[weekly_sales.csv](https://educative.io/udata/MvV1yOyo20G/weekly_sales.csv)*, *[features.csv](https://educative.io/udata/Mwqy7d5Ldqn/features.csv)*, and *[stores.csv](https://educative.io/udata/kg7jEz0mVnQ/stores.csv)*. We'll use the pandas library's `pd.read_csv` function to read each CSV file into a DataFrame.

For more on pandas and data processing, check out the [Machine Learning for Software Engineers](https://www.educative.io/collection/6083138522447872/5629499534213120?authorName=Adaptilab) course on Educative.


# Chapter Goals:
- Learn about the retail dataset used in this case study
- Read the separate data files that comprise the dataset


# A. Starting off the project

Let's say you're a machine learning engineer at a large retail corporation, and your supervisor just gave you this dataset and said,

*"I want a system that can make future sales predictions for these 45 stores. We want to know whether they'll make enough money to justify keeping them. Here's a dataset containing the past sales of these stores."*

This is a pretty short and vague description of the project, which is normally the type of description you'd get from a manager or supervisor. Luckily, we can learn more about the project by looking through the dataset.

Industry data usually comes in CSV files, XLSX spreadsheets, JSON data files, or can be accessed from a database using SQL. In this case, our dataset comes in three CSV files: *[weekly_sales.csv](https://educative.io/udata/MvV1yOyo20G/weekly_sales.csv)*, *[features.csv](https://educative.io/udata/Mwqy7d5Ldqn/features.csv)*, and *[stores.csv](https://educative.io/udata/kg7jEz0mVnQ/stores.csv)*. We'll use the pandas library's `pd.read_csv` function to read each CSV file into a DataFrame.

For more on pandas and data processing, check out the [Machine Learning for Software Engineers](https://www.educative.io/collection/6083138522447872/5629499534213120?authorName=Adaptilab) course on Educative.


Learn about the retail dataset used for the project.

Preliminary Data Analysis

Data Processing

Model Predictions

Conclusion

The Dataset

Chapter Goals:

A. Starting off the project