The human body is detected with the help of theMediapipelibrary. Then, using the mathematical methods applied, it is determined how much the exercise count is done.

Github Project Link: https://github.com/Furkan-Gulsen/Sport-With-AI

- Introduction
- Importing Libraries
- Exploring the Dataset
- Processing Dataset
- Logistic Regression
- Logistic Regression without sklearn
- Logistic Regression with sklearn
- Layer Neural Network

- Machine Learning refers to machine learning to use big data sets instead of hardcoded rules.
- Machine Learning allows computers to learn on their own. This type of learning takes advantage of the computing power of modern computers that can easily handle large data sets.

**Supervised Learning involves using tagged data sets with inputs and expected outputs.**

As you train an AI using supervised learning, you give it an input and say the expected output. If the output produced by AI…

Reindexing row labels and column labels changes a DataFrame. It means Reindex fits the data to match a specific set of tags along a specific axis. Multiple operations can be performed through indexing as follows:

- Reorder existing data to match a new set of labels.
- Add missing value (NA) markers to tag positions where the tag is not data.

You should be aware of three important ways to apply functions of your own or another library to pandas objects. The appropriate method to use depends on whether your function is waiting to run on the entire DataFrame, row, or column-wise or element-wise.

- Table Function Implementation:
**pipe ()** - Row or Column Function Implementation:
**apply ()** - Element Function Implementation:
**applymap ()**

Custom operations can be performed by passing the appropriate number of parameters as function and pipe arguments. Thus, the processing is performed on all data. For example, add 2 as a value to all items in the Dataframe.

Now…

Numerous methods collectively calculate descriptive statistics and other related processes in the Dataframe. These are aggregations like sum(), mean(), but some produce an object of the same size, such as sumsum(). In general, these methods take an axis argument like ndarray, {sum, std,…}, but can be specified by the axis name or integer.

Let’s create a DataFrame and use this object throughout this section for all operations.

So far, we have learned the three pandas data structure and how to create them. Due to its importance in real-time data processing, we will focus on dataframe objects right now and mention a few other data structures.

**axes:**Returns the list of row axis tags.**dtype:**Returns the dtype object.**empty:**Returns false in serial empty job.**ndim:**Returns the number of dimensions of the underlying data as definition 1.**size:**Returns the number of basic data items.**values:**Returns the series as ndarray.**head:**Returns the first n lines.**tail:**Returns the last n lines.

Let’s consolidate the…

The panel is a 3D data container. Panel data are derived from econometrics and are partly responsible for the name pandas.

There are some semantic values to describe operations involving panel data.

**items:**axis 0 corresponds to a DataFrame in each item.**major_axis:**axis 1 is each row DataFrame.**minor_axis:**axis 2, each column is the DataFrame.

A Panel is created using the following structure:

Parameters of the above structure:

**data:**The data takes various forms such as ndarray, serial, map, series, dict, constants and another DataFrame.**items:**axis = 0**major_axis:**axis = 1**minor_axis:**axis = 2**…**

A data frame is a two-dimensional data structure, that is, the data is aligned in rows and columns in a table. DataFrame Features:

- Potentially columns are of different types
- Size can be changed
- Consists of rows and columns
- Arithmetic operations can be done in rows and columns

DataFrame parameters:

**data**: The data takes various forms such as ndarray, serial, map, list, dictation, constants and other data such as DataFrame.**index**: index is used optionally. Sets row**columns**: Optionally used for column processing.**dtype**: The data type of each column.**copy**: False the default value. …

What I will tell in this article is very different in real projects. In real projects, object detection is not done with this method. This is just one of the steps to be taken when object detection. Here we will start with object detection and counting from the step. I will consider the more advanced algorithms of this, the method of application in the real world, in more detail in my next article.

First of all, let’s load our libraries.

I choose a picture with coins for this job.

Let’s import this picture.

If you notice, you can…

To add the Pandas to Python, you need to write the code below to the terminal and install the Pandas.

`pip install pandas`

The Pandas library in Python deals with 3 data types:

- Series
- DataFrame
- Panel

These data structures are built on numpy. This means they are fast.

Let’s liken this to matryoshkas. What is matryoshkas logic? The nesting of shapes in decreasing dimensions. The logic is the same here. It includes the largest, that is, other sub-dimensions with the largest size.

AI & Full Stack Engineer