Jasurbek Mamurov

Trip to Samarkand ⭐

2023-09-12T10:08:43.169Z

A wonderful chance to feel the vibe of the jewel of the Silk Road

Trip: Basic info ✏️

Points of the trip

Paper factory (ethno-village)
Mirzo Ulugbek Observatory
Mahalla Osh (lunch)
Mausoleum of the Timurids (Gur Emir)
Registan Square
Bibi Khanum Mosque
Mausoleum of Islam Karimov
Necropolis Shahi Zinda

Program

04:30 AM - Gathering of students, handing out insurance policy, boarding the bus.

05:00 AM - Departure to Samarkand.

06:00 AM - Breakfast distribution.

07:00 AM - Sanitation stop.

07:30 AM - Water distribution on the bus.

10:00 AM - 11:00 AM - Arrival in Samarkand.

01:00 PM - 02:00 PM - Lunch of Mahalla Osh (includes full Samarkand pilaf with salad, bread and tea).

! After lunch, there's touring of the remaining locations and returning home.

! There is a snack giveaway on the bus when returning home.

The purpose of this trip is to unite new incoming students, create new members of the IUT family, create unforgettable first impressions of the university, visit the sights of the ancient beautiful city of Samarkand. During the trip, we will follow the program provided above and visit the mentioned places. In between these locations, the visitors will enjoy a unique Samarkand pilaf in one of the most favorite places of Samarkanders “Mahalla Osh”.

"My life highlights" by Jasurbek Mamurov

2023-04-20T11:55:10.523Z

If you're ready to see delicious moments, then let's go. I don't want to waste sheets of paper for proofs when there's a better way of doing this online which can show video proofs too :)

AI Rewind 2022 - The biggest AI conference in Uzbekistan

Photo highlights

Together with the organizers

People who came to see our event

I was one of the moderators. A moment from our performance

At the end of our performance. A group photo.

Video highlights

Feel how it was directly from the video

Appreciation Day

Was awarded for contributing to thr social life of IUT

Was awarded for participating in the "Beruniy" state schoolarship

Click Day

The general vibe

With the IUT students

Arm Wrestling Contest

We don't forget to light a spark in lives of our students at IUT dormitory

Inter-University Debates

It's amazing and we're proud of being representatives of our IUT in various events

Digital Generation Uzbekistan

I've discovered a new family of enthusiasts who just love to share their knowledge

Urban.Tech Uzbekistan Hackathon

Any event, even a hackathon is more interesting with your team

Meeting new faces; constructing a networking

Feeling the taste of a victory

Not just words but feelings :)

Becoming a member of TOP-100 students' family by Ziyo Forum

Not just a collection of TOP's but the collection of a family

invitedPodcast Project

Memorandum among 7 universities for a collaboration

ML Gap by MLC

Our second ML Gap by MLC

Our first ML Gap by MLC

ML Meetup by MLC

Summer University in Tyumen, Russia

...

It's not the end of my journey, there're more things to come, but we'll take only important and rememberable ones for making everything possible with a collaboration, friendship, and love!

Thank you for your attention 💙

...

RNN

2023-03-09T14:45:37.381Z

Wait! What is actually RNN? 🤨

Well, RNN stands for "Recurrent Neural Network". You might wonder why we have some other NN (neural network) other than the traditional one. Trust me, I was in the same situation, my friend)

When we look at the traditional NN's, we can surely say that all the inputs and outputs, in there, are independent of each other. That's true, but what if we need to remember the previous steps?

Here comes the help of RNN. It's a type of NN but the output from the previous step are fed as input to the current step. It's like predicting next words of some sentence by looking at the previoud words. Issues with remembering are solved via the "Hidden Layer" in RNN, and RNN's really delicious feature is it's "Hidden State" (remembers the info about the sequence).

Credits: GeeksforGeeks

Let's break the concept a little bit 😏

Let's say that some calculation has been done. The RNN has it's own memory to remember that. While performing exactly the same task on the hidden layers and inputs to get the result (output), it just uses the same parameters for each input.

Diving deeper ⚠️

Credits: GeeksforGeeks

Okay! Here, we've somewhat a depper network. Three circles represent three hidden layers. These layers have their own w (weights) and b (biases). Since it is so, they don't remember the previous outputs, hence these layer are independent. Right?

It was just some NN, but how does the RNN deal with this? ~Well, by giving the same b's and w's to all layers, the RNN converts the independent activations into dependent ones. Here, it'll be reducing the complexity of increasing parameters and memorizing each previous result and giving it to the next hidden layer as the input.

Since, now, we've the same b's and w's, we can reduce the above network (reduce the number of hidden layers) with the help of RNN. The result will be a somewhat simpler network with a single recurrent layer 👇

Credits: GeeksforGeeks

Sweet formulas ✖️➕➖➗🟰

The formula for calculating the current state:

The formula for applying Activation function (tanh):

The formula for calculating output:

Are we done? ~No, let's see how we can train through RNN 🤔

I. The input's single-time step is given to the network.

II. Calculate that's current state using a set of current input and the previous state.

III. Here, ht becomes ht-1 for the next time step.

IV. It's possible to go as many time steps according to the problem and join the info from all the previous states.

V. It's time to calculate the output using the final current state when all the time steps are completed.

VI. The output is now compared to the actual output. In this case, the target output and the error are generated.

VII. The error is now back-propagated to the network to update the weights and hence the RNN is trained :)

Where do we apply RNN? 😶‍🌫️

Time series forecasting
Machine Translation
Speech recognition
Language modelling and generating text, and so on...

Pros of RNN 👍

Through time, an RNN can remember each and every piece of info. In cases of time series prediction, it can be really useful due to the feature to remember previous inputs as well. This is called "Long Short Term Memory".

To extend the effective pixel neighborhood, the RNNs are even used with convolutional layers.

Cons of RNN 👎

Training an RNN is a very difficult task.

If using tanh or relu as an activation function, it cannot process very long sequences.

Gradient vanishing and exploding problems.

Wanna more? ~Here are some awesome resources 💡

How Recurrent Neural Networks work

An Introduction to Recurrent Neural Networks and the Math That Powers Them

What is Recurrent Neural Network (RNN)? Deep Learning Tutorial 33 (Tensorflow, Keras & Python)

Credits

Most of the concepts and theories were inspired and taken from https://www.geeksforgeeks.org

Huge thanks for providing such a wonderful explanation for such a difficult topic)

Programming

2023-01-08T04:50:45.670Z

Python Math
File Handling
Generators
List comprehensions
Named Tuples

Generators

# def square_numbers(nums):
# for i in nums:
#    yield (i*i) 

# my_nums = square_numbers([1,2,3,4,5]) 

my_nums = (x*x for x in [1,2,3,4,5]) 
print list(my_nums) # [1, 4, 9, 16, 25] 

# for num in my_nums:
#    print num

List comprehensions

# nums = [11, 22, 33, 44, 55, 66]
# Har bir nums dagi 'n' uchun 'n' ni xohlayman
# my_list = list()
# for num in nums:
#    my_list.append(num)
# print(my_list)
# 
# my_list = [n for n in nums]
# print(my_list)

# my_list = map(lambda n: n, nums)
# print(list(my_list))

# my_list = list()
# for num in nums:
#    if not num % 2 == 0:
#    my_list.append(num)
# print(my_list)

# my_list = [n for n in nums if not n % 2 == 0]
# print(my_list)

# my_list = filter(lambda n: not n % 2 == 0, nums)
# print(list(my_list))

# Biz 'abcd' dagi har bir harf uchun '12' 
# sonlarini (harf, son) juftligicha xohlaymiz
# my_list = list()
# for letter in "abcd":
#    for number in range(1, 3):
#       my_list.append((letter, number))
# print(my_list)

# my_list = [(letter, number) for letter in 
# "abcd" for number in range(1, 3)]
# print(my_list)

# names = ["Taylor", "Daniel", "Tim", "Elon", "Christopher"]
# jobs = ["Singer", "Actor", "CEO(Apple)", "CEO(Twitter)", "Filmmaker"]
# # pair = zip(names, jobs)
# # print(list(pair))
# # my_dict = dict()
# # for name, job in zip(names, jobs):
# #    my_dict[job] = name
# # print(my_dict)

# my_dict = {job: name for name, job in zip(names, jobs) if name != "Tim"}
# print(my_dict)

# nums = [1, 1, 2, 1, 3, 4, 3, 4, 5, 5, 6, 7, 8, 7, 9, 9]
# my_set = set()
# for num in nums:
#    my_set.add(num)
# print(my_set)

# my_set = {n for n in nums}
# print(my_set)

# nums = [5, 6, 7, 8, 9, 10]
# 'nums' dagi har bir 'n' uchun 'n*n' ni xohlayman
# def gen_funct(numbers):
#    for num in numbers:
#       yield num * num

# my_gen_funct = gen_funct(nums)
# for x in my_gen_funct:
#    print(x)

# my_gen_comp = (n * n for n in nums)
# for x in my_gen_comp:
#    print(x)

Named Tuples

from collections import namedtuple 

# list / tuplecolor = (55,155,255) 

# dictionarycolor = {'red': 55, 'green': 155, 'blue': 255} 
# namedtupleColor = namedtuple('Color', ['red', 'green', 'blue'])

color = Color(blue=55,green=155,red=255)

from collections import namedtuple 

Color = namedtuple('Color', ['red', 'green', 'blue']) 
color = Color(55,155,255)
white = Color(255,255,255) 

print color.blue

That's it.

EDA

2022-12-24T10:19:39.769Z

'' What in the world is the EDA? ''

Developed in 1970s by John Tukey, EDA (Exploratory Data Analysis) can be said as the 1st step in data analysis process. When we talk about statistics, EDA is a summarizing of main characteristics of data sets by analyzing them. We may include visual methods that are often used together.

Example ⬇️

Let's say that you're going to learn a new field in IT, and things to consider before making a decision of starting out would be:

Whether that way can give you solutions to your problems or not.
Finding appropriate materials such as documentations, videos, or tools the can make it easy for you to advance.
Can you make it happen at the moment of starting, and can you spend some amount of your time on learning?
etc...

Let's continue 🎮

Similar to this, when you're about to build a machine learning model, you have to be fine with your data whether it's making sense or not. EDA helps getting confidence in our data a point where you're ready to use some ML algorithm.

Source: towardsdatascience.com (Exploratory Data Analysis: A Practical Guide and Template for Structured Data)

Why do we do EDA? 🙋‍♂️

EDA is important before taking a leap to ML or modeling your data. Performing that, we get information whether:

the selected features are good enough to model
all the features required
there are any correlations

Once we have done with EDA and taken important insights, that's feature can be used for unsupervised and supervised ML modeling.

In any ML workflow, you have to provide insights to stake holders in the last step. It is possible to explain every piece of code, but what about the audience? The audience can understand what our data is about and what insights we got from exploring data by referring to the plots, heat-maps, graphs, and so on, after the completion of EDA.

Coming to our last example, we can say that there will be enough interest in our fiends to go with us in our chosen field due to the details provided before making a decision.

Steps in EDA 🪜

There are many steps for performing EDA. Let's see just some of them:

Description of data (we need to know the various kinds of data and other stats of the data)
Handling missing data (real-world data is not always clean and homogeneous)
Handling outliers (detecting something separate or different from the crowd)
Understanding relationships and new insights through plots (by visualizing data set, getting many relations)

Source: towardsdatascience.com (Exploratory Data Analysis …A topic that is neglected in Data Science Projects)

Tools used for EDA 🔎

For automating the steps of predictive modeling like data cleaning and data visualization, there are many open-source tools such as Tableau, Excel, Weka, Qlikview, and so on.

We can do EDA, in programing, using R, SAS, and Python, and the important packages in Python are:

Matplotlib
Pandas
Numpy
Seaborn
Bokeh

What if we don't use EDA at all? ❌

That will be a mistake with many implications:

generating inaccurate models
generating on the wrong data
not creating the right type of variables
using resources inefficiently

So, don't be in a hurry and think carefully in every step since most of the things depend on your actions, my friend 😉

We're not done with EDA but only starting. Let's use its power and make ourselves powerful 💪

Credits

I want to express my gratitude to the website towardsdatascience.com and especially sunil kumar for providing an awesome explanation about EDA with the title of "Exploratory Data Analysis …A topic that is neglected in Data Science Projects".

Data Visualization

2022-12-20T08:44:25.865Z

⭐ Enjoying real beauty of programming ⭐

Basic information

Looking at the world today, we can say WOW to the amount of data that's being generated on a daily basis. If you're given big data in a raw format and asked to find some trends, it would be possible to see in what condition you will be at that moment 😁

-> For the rescue, there comes power - Data Visualization (💪)

With its help, we can understand almost all data since that's given in pictorial representation in an organized way.

Our friend Python, gives us enough chance by providing a plenty of libraries with various features. I haven't yet mentioned about the awesome graphs...

If you're ready, let's discover the worlds of Plotly, Seaborn, and Matplotlib 🚀

Oooh, wait for a sec 🖐️

Let's install those libraries. Are you familiar with our old friend - `pip`?

Python Workshop - Installing Packages

Matplotlib

You're already familiar with NumPy, right?

Well, matplotlib is built on NumPy arrays and it's low-level data visualization library in Python. Matplotlib includes wonderful plots, and you are having a chance of using them from now on.

Popular plots in matplotlib

Scatter Plot - for observing relationships between variables using dots
Line Chart - for representinf a relationship between two data X and Y on a different axis
Bar Chart - for representing the category of data with rectangular bars with lenghts and heights that are proportional to the values which they represent
Histogram - for representing data in the form of some groups.

More information setting up an environment with matplotlib

Seaborn

Let's move a little higher!

Seaborn is a high-level interface built on top of the Matplotlib (it can be used with Matplotlib as well). It gives us an opportunity to play with beautiful design styles and color palettes to make atrractive graphs.

Using them together is an easy process. We just have to invoke the Seaborn Plotting function as normal, and then we can use Matplotlib's customization function.

ℹ️ Seaborn comes loaded with dataset such as iris, tips, etc...

Plotly

It allows us to detect any outliers or anomalies in numerous data points with the help of tool capabilities. With it, we can have more customization and it makes the graph more attractive.

Plotly also provides different interactions such as creating dropdown menu, adding buttons, creating sliders, and selectors

You can enjoy the functionalities by looking at the materials provided in the following section ✅

Thank you for your time! We're glad that you are learning with us 😉

Documentations - 💪

Video materials - 🔥

Matplotlib Tutorials (Corey Schafer)
Seaborn Beginner to Pro | Seaborn Tutorial for Beginners | Seaborn Playlist (Learnerea)
Plotly Python Tutorials - data visualization in python (Data Science Tutorials)
Plotly | YouTube Channel

Credits

Almost all materials have been provided to you with the help of GeeksforGeeks

Git & GitHub

2022-12-19T08:18:09.287Z

Are you ready to jump into the world of VCS?

That's awesome. Let's do that together!

Basic background

What is VCS and how it functions? 🤔

Version control is a system that records changes to a file or set of files over time so that we can recall specific versions later.

3 types of VCS's

⬇️ ⬇️ ⬇️ ⬇️

Local VCS

Only for applying modifications inside your own computer.
If anybody needs some version, that person should come and take the version by copying that into their flash drive.
If something is accidentally deleted, you cannot get that afterwards if others had not copied that beforehand.

Centralized VCS

There is a separate machine that saves the versions of your files.
If something is deleted from your computer, just recover that from the above machine.
But, what if the machine will stop working as well???

Distributed VCS

Each computer has a VCS on it.
Now, we can recover information confidently.

Dive into Git & GitHub

What power do we have now? 💪😎👍

Distributed VCS is the real power. We can see that by just looking at Git.

Git Features

Distribution
Size and Speed
Data Assurance
Open Source
Branching and Merging
Detailed information about them - https://git-scm.com/about

Git installation

Git download page - https://git-scm.com/downloads

Windows: https://git-scm.com/download/win
MacOS: brew install git
Ubuntu: sudo apt-get install git-all

Configuration

Template: git config --global <key> <value>
-> git config --global user.name "Your Name"
-> git config --global user.email your@email.com

File States

The ”git commit” command captures a snapshot of the project's currently staged changes.
“git add” tells that you want to include updates to a particular file in the next commit

Commits & Branches

A branch in Git is simply a lightweight movable pointer to one of commits.
Branching means, you diverge from the main line of development and
continue to do work without messing with that main line

*HEAD is one of the pointers. For every branch, there's a *HEAD pointing to the last commit.

Commit

-> git add <filename>
-> git commit -m "a clear message"

Git add

Add changes in working directory to the staging area:
-> git add <filename> [<filename>]
A command that accepts wildcards as parameters:
-> git add *.py
A dot ‘.’shortcut is used to add all files:
-> git add .
For tracking current changes, use:
-> git status

It is not recommended to do the git add . and git add -A for not adding unnecessary files.

.gitignore

A gitignore file specifies intentionally untracked files that Git should ignore. Files already tracked by Git are not affected. Each line in a gitignore file specifies a pattern. Detailed explanation: https://git-scm.com/docs/gitignore

Git commit

“git commit” is used to commit the staged files to the repo. 
The default file editor will be opened to allow you to add commit message:
-> git commit
Use -m parameter to add inline commit message instead:
-> git commit -m “first commit”
Add staged changes to the last commit:
-> commit --amend

In the process of using commit --amend, we can also change the message of the commit. To avoid that, we can use a flag --no-edit

Branches

View the list of existing branches:
-> git branch
Create a new branch:
-> git branch feature

Switch to the branch:
-> git checkout feature
Short alias to create new branch and switch to it:
-> git checkout -b feature

When we create a branch, it is created from the last commit that is in the current branch

Merging

Just imagine you have the repository represented, and you need to have your feature
in the master branch.

We can use git merge command.
Git creates a new snapshot and automatically creates a new commit that points to it. This is called as a merge commit and it has more than one parent

-> git merge feature

If there's a conflict on merging branches, Git will open a git merge and show on which files you have conflicts. And, you have to deal what way to choose.

Rebasing

It is the process of moving the base of our branch from one commit to another making it appear as if we had created our branch from a different commit.

-> git rebase master

It is a powerful feature. But, there could be some issues related to commits, so make sure that only you are working on one branch.

How to get a repository?

Create a new repo:
-> git init
Get an existing repo:
-> git clone https://github.com/username/repo

Default name for remote repo is origin

Push & Pull (changes from the server)

To update remote refs using local refs and simply push changes to 
remote repo: 
-> git push

To take changes from remote repo and try to merge them to our local one:
-> git pull 
It also works like a combination of merge and fetch commands for our local 
changes.

Commit History & File Changes

To show full commit history:
-> git log
To list all comments which were made from <commit 1> to <commit 2>
(<commit 1> is not included):
-> git log <commit 1>..<commit 2>
To show differences between files in two commits or between our 
current repo and a previous commit:
-> git diff

Hu-uh! 😶‍🌫️

That's a lot of information.

It is not easy to grasp that much details at first, but that doesn't mean it's impossible. It happens with almost everybody. Those who have found a special key can learn everything, and that key is consistency, my friend 😎

Thank you for your time with us. Keep learning and winning 🚀

Need more?

What is version control? (atlassian) - https://www.atlassian.com/git/tutorials/what-is-version-control
SSH generation - https://docs.github.com/en/authentication/connecting-to-github-with-ssh/generating-a-new-ssh-key-and-adding-it-to-the-ssh-agent
Git branching interactive tutorial - https://learngitbranching.js.org/
Pro Git book - https://git-scm.com/book/en/v2
Comparing Git Workflows: What You Should Know (atlassian) - https://www.atlassian.com/git/tutorials/comparing-workflows

Video materials 📺

Git Tutorial for Beginners: Command-Line Fundamentals (Corey Schafer) - https://www.youtube.com/watch?v=HVsySz-h9r4&list=PL-osiE80TeTuRUfjRe54Eea17-YfnOOAx
Getting started with Git & GitHub (Start your own projects!) (Caleb Curry) - https://www.youtube.com/watch?v=SExhUmE7OLA&t=1s
Git + GitHub Branches, Forks, and Pull Requests (Caleb Curry) - https://www.youtube.com/watch?v=oa1wXWeH1IQ&t=339s

Credits 👏

EPAM Training Center - All of the materials have been taken from the EPAM Python Training 2022.03. I express my gratitude to them for providing such great details on trending topics. Hope, you enjoy this as well!

Jasurbek Mamurov

2022-10-01T17:18:27.038Z

Huge thanks to the author of this photo)))

Who am I?

- A student like you who is a junior at the time you are reading this text -

- A student who hurries because of deadlines and tries to avoid postponing them :) -

- A person who dreams big and who intends to change everything -

(Not everything, but OK!)

What things can I show you to get your interest?

I mean from the past...

- Have you heard about the Machine Learning Club at INHA?

~ Well, with the help of my amazing friends, we have put an initial fire to start this club, this community.

- Why?

~ We don't want you to fall into holes of hopelessness in your learning but try your best with fun with your friends, your community!

- I am not an ML specialist but want to try other things!

No problem. But, do you know that you can achieve literally just everything by learning in a group of students like you?

- Yeah, I know that. But, how can I create my own community?

~ You are at INHA my friend and you have us. Do you think that we don't care about you? It is not true. We are with you :)

- Oooooooo, coooool 😲🥹

For now, just try a little piece of 🍰 and taste the things we have done 😏

Open Meeting @ IT-Park

ML Party @ IMPACT.T

I know that it is not enough( and you need more...

So, why don't you come to presidential debates on 10th of October and see what I am going to give you for the rest of your university life? 😉

My amazing friend, I would wait YOU on the debates in the room B304 🤙

If you want to contact me?)

Telegram Instagram Facebook LinkedIn

#expectmore

#your_vote_matters

#vote_for_justice

Thanks for reading!

Have a great day, my friend)))

Taking a leap in ML 🚀

2022-05-26T12:45:51.893Z

Designed on Canva.

Introduction

We all know about dependent and independent variables, right? Well, in the linear regression, we focus only on the linear relationships between them. But, what about nonlinear relationships? 😕

🥁🥁 Let me introduce you the "Decision trees"

Into the decision trees

They're made to capture nonlinear relationships and they model data as a tree of hierarchical branches. Its structure is a flowchart-like in which:

each internal node represents a test on an attribute (e.g. whether a coin flip comes up heads or tails)
each branch represents the outcome of the test
each leaf node represents a class label (decision taken after computing all attributes).

The paths from the root to the leaf represent classification rules. BTW, the decision trees can adapt to both regression and classification tasks.

Common terms

Root node

It represents the entire population or sample, and this further gets divided into two or more homogeneous sets.

Splitting

It is a process of dividing a node into two or more sub-nodes.

Decision node

When a sub-node splits into further sub-nodes, then it is called a decision node.

Leaf/Terminal node

Nodes that do not split are called Leaf or Terminal node.

Pruning

When we remove sub-nodes of a decision node, this process is called pruning. It is the opposite process of splitting.

Branch/Sub-tree

A subsection of the entire tree is called branch or sub-tree.

Parent and Child node

A node, which is divided into sub-nodes is called a parent node of sub-nodes, whereas sub-nodes are the children of the parent node.

Any examples?

In this example, we want to classify a person as unfit or fit based on:

the person’s age
whether he/she eats pizza
whether he/she exercises in the morning

A decision tree of this could be:

The example is given in the context of decision trees.

From the diagram, we can see that at every node there is a yes/no decision. We keep moving in the tree until we reach the leaf nodes, where the observation is classified into a class.

Let's Python

First of all, download the dataset: Audit Risk Dataset of different firms. We will be performing the binary classification task of predicting whether a company is fraudulent or not.

Let's look at the dataset's attributes

Audit Risk Dataset
# Sector_score
# LOCATION_ID
# PARA_A
# SCORE_A
# PARA_B
# SCORE_B
# TOTAL
# numbers
# Marks
# Money_Value
# MONEY_Marks
# District
# Loss
# LOSS_SCORE
# History
# History_score
# Score
# Risk : BInary Target Variable

Fortunately, sklearn package has a lot of machine learning models implemented as classes and we will be importing the DecisionTreeClassifier class from sklearn.tree. We will also be importing a function named train_test_split from sklearn.model_selection that divides our dataset into train and test sets.

 1  import pandas as pd
 2  from sklearn.tree import DecisionTreeClassifier
 3  from sklearn.model_selection import train_test_split
 4  from sklearn.metrics import accuracy_score,classification_report
 5
 6  df = pd.read_csv('audit_data.csv')
 7
 8  # MAKE DATA
 9  X = df.drop(columns = ['Risk','LOCATION_ID'])
10  Y = df[['Risk']]
11
12  X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size = 0.2, random_state = 3)
13
14  # MAKE MODEL
15  d_tree = DecisionTreeClassifier()
16  d_tree.fit(X_train,Y_train)
17
18  # CALCULATE AND PRINT RESULTS
19  preds = d_tree.predict(X_test)
20  acc = accuracy_score(y_true = Y_test,y_pred = preds)
21  print(acc)
22  print(classification_report(y_true = Y_test,y_pred = preds))

After we read the data in line 6, we separate our target variable as Y.

We drop the LOCATION_ID column since it would not provide any useful information to the model.

To split the data into training and test sets, we use the function train_test_split. We provide our inputs, X, and the labels, Y, to the function in line 12. We also provide the test set size as test_size. 0.2 implies that 20% data will be included in the testing set, while the rest 80% will form the training set. The function outputs 4 items that we can retrieve directly into 4 variables. These are:

Inputs for the training data that we store in X_train
Inputs for the testing data that we store in X_test
Labels for the training data that we store in Y_train
Labels for the testing data that we store in Y_test

In line 15, we make our Decision Tree model. We call DecisionTreeClassifier without any arguments. Then in the next line, we call the fit function of the model. We provide the training examples and labels to the function.

Now, we need to evaluate our model. Therefore, we use the predict function of the model in line 19 to store predictions in preds. We give the testing inputs X_test to predict as an argument.

We use the accuracy_score function to measure the accuracy of the predictions. We print the accuracy with the classification report, which we obtained by using the classification_report function, in the last two lines.

From the outputs, we can see that the model performs excellent on the testing data. The model has learned all patterns and relationships in the dataset and gives correct results 100% of the time.

We might not get 100% accuracy if we have had bigger and more complex datasets

This is the ending of the post dedicated to Decision Trees.

Thanks for your time and effort.

Keep learning and exploring 🌎

Credits to:

Educative and Kaggle. Thanks for providing amazing and useful materials.

The content of this article is inspired by and taken from Educative.

The dataset used in the example above is taken from Kaggle.

Let's continue the ML...

2022-05-21T10:08:18.972Z

As you remember, we have seen a lot of things about linear regression and attempted real-life projects to strengthen our gained knowledge. 💪

Let's continue our journey and a little increase our temp with the "Logistic Regression" 🙂🙂🙂

What in the world the Logistic Regression is?

By the way, I want you to imagine a kind of dataset in your mind and refer to it when talking about some challenging concepts to simplify our understanding

Until this point, you might have been predicting some numerical quantities via your models. But what about a categorical variable?

In statistics, a categorical variable is a variable that can take on one of a limited, and usually fixed, number of possible values, assigning each individual or other unit of observation to a particular group or nominal category on the basis of some qualitative property. More on Wikipedia.

The categorical data is divided into classes and the task of predicting it is known as classification which can be performed using logistic regression. In classification problems, the predicted variable is categorical. The simplest case of classification is when the predicted variable is binary, i.e., it has only two classes, e.g., yes/no, male/female, etc.

The logistic regression takes the linear combination of different variables plus the intercept term (like with the linear regression), but after that, it takes the result and passes it to a logistic function which is also known as sigmoid and defined as:

The formula of the sigmoid function. The "t" is the output of the linear combination of variables plus the intercept term.

The plot of the logistic function.

The logistic function has a fixed range from 0 to 1. Clearly, only the numbers between 0 and 1 are taken as the output.

The prediction function. "g" is the sigmoid and f is given below as:

The linear combination of variables plus the intercept term.

The whole concept is explained by the picture.

In logistic regression, the output is interpreted as the probability of the observation belonging to the second class. In binary classification, when the result is greater than 0.5, the observation belongs to the second class, and when it is less than 0.5, it belongs to the first class.

Cost function

The following is the math-related part and I recommend you to try to understand it by spending more time than other parts. YOU CAN DO IT!

The cost function used instead of mean squared error is the cross-entropy function.

The y(with the index of i) denotes labels of our classes. It can be 1 or 0 for binary classification.The expression inside the square brackets is the loss for one observation. The error is summed for all observations. The function will be minimized using gradient descent, as can be also done for linear regression. However, we will not go further into the math of how gradient descent would optimize this function at this point.

Logistic Regression in Python

We would not create the bycicle from the beginnig but use the LogisticRegression class available in sklearn.linear_model.

To evaluate the performance, we will be using the function accuracy_score from sklearn.metrics, which tells us the percentage of accurate results.

We will be predicting whether a credit card client defaults or not by using the Credit Card Clients Default Dataset. The binary prediction variable is default.payment.next.month

 1  import pandas as pd
 2  from sklearn.linear_model import LogisticRegression
 3  from sklearn.metrics import accuracy_score
 4
 5  df = pd.read_csv('credit_card_cleaned.csv')
 6
 7  # Make data
 8  X = df.drop(columns = ['default.payment.next.month','MARRIAGE','GENDER'])
 9  Y = df[['default.payment.next.month']]
10
11  # Fit model
12  lr = LogisticRegression()
13  lr.fit(X,Y)
14
15  # Print parameters
16  print(lr.coef_)
17  print(lr.intercept_)
18
19  # Get predictions and accuracy
20  preds = lr.predict(X)
21  acc = accuracy_score(y_true = Y,y_pred = preds)
22
23  print('accuracy = ',acc)

Output:
[[-2.57824834e-05 -3.89563030e-06 -3.62189243e-05 -4.66762409e-04
   8.12276762e-05 6.51340113e-05 5.46246420e-05 5.07101652e-05
   4.57317929e-05 4.16325749e-05 -9.45615078e-06 5.15966173e-06
   2.05599697e-06 2.85369917e-06 1.79368256e-06 2.03851811e-06
  -3.21462059e-05 -2.15839860e-05 -8.56968053e-06 -8.44288217e-06
  -6.25973049e-06 -1.84750686e-06]]
[-1.73101261e-05]
accuracy = 0.778792322047454

We load the data in line 5. Then we separate our training data and the predictions in lines 8 and 9. We initialize the class in line 12. We use the fit function to fit the model and obtain the best parameters in line 13. Then we print the model parameters and the intercept parameter in lines 16 and 17. Afterward, we obtain predictions using the predict function. We calculate the accuracy in line 21. accuracy_score expects the actual values and the predicted values. Then we print the accuracy in the last line.

From the output, we can see that our model gives the correct prediction 77% of the time.

After consuming this much info successfully, you would also be provided with the explanation of evaluation of your logistic regression models. Until that time, spend your time on this and try to understand by giving your own examples to yourself.

Let's do it!

🚀

Credits to:

Educative, Kaggle and Wikipedia.

The contents, concepts, and especially codes are taken from the Educative.

Explanations of some difficult concepts are from the Wikipedia.

The dataset used in the example is taken from the Kaggle.

Jasurbek Mamurov

Trip to Samarkand ⭐

Trip: Basic info ✏️

"My life highlights" by Jasurbek Mamurov

If you're ready to see delicious moments, then let's go. I don't want to waste sheets of paper for proofs when there's a better way of doing this online which can show video proofs too :)

AI Rewind 2022 - The biggest AI conference in Uzbekistan

Photo highlights

Video highlights

Appreciation Day

Click Day

Arm Wrestling Contest

Inter-University Debates

Digital Generation Uzbekistan

Urban.Tech Uzbekistan Hackathon

Becoming a member of TOP-100 students' family by Ziyo Forum

invitedPodcast Project

Memorandum among 7 universities for a collaboration

ML Gap by MLC

ML Meetup by MLC

Summer University in Tyumen, Russia

...

It's not the end of my journey, there're more things to come, but we'll take only important and rememberable ones for making everything possible with a collaboration, friendship, and love!

Thank you for your attention 💙

...

RNN

Wait! What is actually RNN? 🤨

Let's break the concept a little bit 😏

Diving deeper ⚠️

Sweet formulas ✖️➕➖➗🟰

Are we done? ~No, let's see how we can train through RNN 🤔

Where do we apply RNN? 😶‍🌫️

Pros of RNN 👍

Cons of RNN 👎

Wanna more? ~Here are some awesome resources 💡

Credits

Programming

Generators

List comprehensions

Named Tuples

EDA

'' What in the world is the EDA? ''

Example ⬇️

Let's continue 🎮

Why do we do EDA? 🙋‍♂️

Steps in EDA 🪜

Tools used for EDA 🔎

What if we don't use EDA at all? ❌

We're not done with EDA but only starting. Let's use its power and make ourselves powerful 💪

Credits

Data Visualization

⭐ Enjoying real beauty of programming ⭐

Basic information

If you're ready, let's discover the worlds of Plotly, Seaborn, and Matplotlib 🚀

Oooh, wait for a sec 🖐️

Let's install those libraries. Are you familiar with our old friend - pip?

Matplotlib

Seaborn

Plotly

Thank you for your time! We're glad that you are learning with us 😉

Documentations - 💪

Video materials - 🔥

Credits

Git & GitHub

Basic background

3 types of VCS's

⬇️ ⬇️ ⬇️ ⬇️

Dive into Git & GitHub

Git Features

Git installation

Configuration

File States

Commits & Branches

Commit

Git add

.gitignore

Git commit

Branches

Merging

Rebasing

How to get a repository?

Let's install those libraries. Are you familiar with our old friend - `pip`?