Machine learning is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence that uses algorithms to learn from data and make predictions or decisions without being explicitly programmed to do so.

There are three main types of machine learning: supervised learning, unsupervised learning, and reinforcement learning.

Supervised learning is where an algorithm is trained on labeled data, meaning the desired output (or “label”) is provided for each input. The algorithm then makes predictions about the output for new data. Examples include linear regression and logistic regression.

Unsupervised learning is where the algorithm is not provided with labeled data and must find patterns or relationships on its own. Examples include clustering and dimensionality reduction.
Reinforcement learning is a type of machine learning in which an agent learns to make decisions by interacting with its environment and receiving feedback in the form of rewards or penalties.
Machine learning is widely used in a variety of applications such as image recognition, natural language processing, self-driving cars, fraud detection and many more.

How machine learning works?

Machine learning algorithms work by using a set of input data, called the “training data,” to learn and make predictions or decisions.

Here is a general overview of the process:

Collect and prepare the data: The first step is to gather and prepare the data that the algorithm will use to learn. This includes cleaning and pre-processing the data, and splitting it into a training set and a test set.

Choose a model and train it: Next, a machine learning model is selected and trained on the training data. The model “learns” the patterns and relationships in the data and creates a prediction function. This process is known as “fitting” or “training” the model.

Evaluate the model: After the model is trained, it is evaluated on the test data to see how well it performs on unseen data. This allows us to gauge the model’s accuracy and make any necessary adjustments.

Make predictions or decisions: Once the model is trained and evaluated, it can be used to make predictions or decisions on new data.

It’s important to note that the process of training a machine learning model requires fine-tuning the parameters of the model and selecting the appropriate model for the task at hand. Also, the accuracy of the model depends on the quality and quantity of the data, the complexity of the model, and the choice of the algorithm.

List of all packages / programs on machine learning using python.

There are many programs and libraries available for machine learning in Python. Here are a few popular ones:

TensorFlow – an open-source library for machine learning and deep learning, developed by Google.

scikit-learn – a library for traditional machine learning, which includes a wide range of supervised and unsupervised learning algorithms.

Keras – a high-level neural networks library, which runs on top of TensorFlow or other backends.

PyTorch – an open-source machine learning library developed by Facebook AI Research.

Theano – a library for fast numerical computation, particularly well-suited for machine learning.

SciPy – a library for scientific and technical computing in Python, which includes modules for optimization, interpolation, and other machine learning-related tasks.

Pandas – a library for data manipulation and analysis, which is often used in preprocessing data for machine learning.

NLTK – a library for natural language processing, which includes tools for text mining and machine learning.

Gensim – a library for topic modeling and document similarity analysis.

LightGBM – a high-performance gradient boosting framework that is used for machine learning tasks.

These are just a few examples of the many libraries and frameworks available for machine learning in Python, and new ones are being developed all the time.

The post Machine Learning appeared first on .

Extracting text from an image using pytesseract tool and package using Python programming.

install tesseract.exe from here.

First, here is an image which contains some text as following..[saved as sample.jpg)

And here is the full code to extract text from above image.

from PIL import Image
#Python Imaging Library (abbreviated as PIL) (in newer versions known as Pillow)
# is a free and open-source additional library for the Python programming language that
#adds support for opening, manipulating, and saving many different image file formats.
import pytesseract
#Python-tesseract is an optical character recognition (OCR) tool for python
import cv2
pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files (x86)\\Tesseract-OCR\\tesseract.exe' 
img = "sample.jpg"
t1=pytesseract.image_to_string(Image.open(img))
#print(pytesseract.image_to_string(Image.open(img)))
print(t1)
file1=open('recognized.txt', 'w')
file1.writelines(t1) 
file1.close()
print("File created successfully!")

And the output from above program is..

As the program just extracted only characters from an image. And also extracted string is stored in text file by using file handling.

The post Text extracting from an Image (OCR ) appeared first on .

In this machine learning example identify face using Python programming.

Package  used in this example is opencv [computer vision]. To install this package simply use following syntax:
pip install opencv-python

import cv2 #pip install opencv-python
# Load the cascade
face_cascade = cv2.CascadeClassifier('face_detector.xml')
# Read the input image
img = cv2.imread('test2.jpg')
# Detect faces
faces = face_cascade.detectMultiScale(img, 1.1, 4)
# Draw rectangle around the faces
for (x, y, w, h) in faces: 
  cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 5) 

#show on screen begins
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Export the result
cv2.imwrite("face_detected.png", img) 
print('Successfully saved')

output of the above program is : 

To download haarcascade face detector xml file follow this link.

The post Face recognition using Python appeared first on .

in the following example we used three packages, they are

a) bs4 [Beautiful Soup for web scraping]
b) pandas [panel data for data representation ]
c) request [to get source / url]

#data science with Python - extracting Gold Price
import bs4 
import pandas as pd 
import requests 

url = 'https://www.goodreturns.in/gold-rates/bangalore.html'
result = requests.get(url) 
soup = bs4.BeautifulSoup(result.content,'html.parser') 
price = soup.find_all('div', {"id":"current-price"})
for pr in price:
    print("Price:", pr.text)
txt=pr.text

from tkinter import *
root=Tk()
root.title('Gold Price')
root.configure(bg='gold')
root.geometry('200x100')
w=Label(root, text=txt, bg='red', font='sans 14')
b=Button(root, text="Close", fg='red', bg='yellow', command=root.destroy)
w.pack()
b.pack()
root.mainloop()

Output of the above example is:

Click here for other programs on Data Science 

The post Data Science – 4 [extract gold price using web scrap] appeared first on .

The Internet of Things is a term which describes how the different devices connect together to transmit data using the network. 

The IoT is an expansion of a computer network where one can easily use on other devices like home appliances, smart tv’s, fitness trackers, robotics vacuum cleaner, etc.

So far we have been uysing internet on our Personal computer or Laptop or on our smartphones that’s just for the sake of information exchange but IoT gave huge opportunities to explore the use of the internet on other said devices and work become smarter.

7 Main Characteristics of IoT

1) Connectivity: Here devices need to be connected.
2) Things: devices which are designed to be connected.
3) Data: Source of Internet
4) Intelligence: Sensing data using Artificial Intelligence or Data Analytics etc.
5) Action: Where real usage of data takes place.
6) Ecosystem: in community goals, organizational goals, etc.
7) Communication: devices get connected so there is a flow of data between machine to machine (M2M).

Types of IoT

a) Industrial IoT : Improving operational efficiency etc.
b) IoE : Internet of everything like People, process, data etc.
c) CIoT : Consumer Internet of Things like Home appliances, smart Tv’s, etc.

IoT is based on the industry standard of IEEE.

Applications of IoT

Home automation: control and automation of lighting, ventilation, air conditioning, robotic vacuums, air purifiers.

Wearable: smart watches, fitness trackers, VR etc.

Environment: IoT application technologies that have sensors can be used to monitor air and water quality, soil or atmospheric conditions, and even the movements of wildlife.

The IoT devices can also be used in applications such as tsunami early-warning systems to enable authorities to offer more effective responses and aid.

Utilities: real-time grid assessment.

Logistics: real-time visibility of location.

How IoT works
To work IoT, the following are essentials

a) Hardware (to communicate other devices)
b) Protocols (set rules to transmit data)
c) Domains (locations to store data)
d) Applications (software to communicate with devices)

You can also check out my video in Hindi on IoT

The post Internet of Things appeared first on .

According to John McCarthy, AI is an ability to interact with the world in the form of speech, vision, motion, manipulation etc.
or Ability to model the world and to reason about it.
or Ability to learn and to adapt rapidly.

Future goals of AI
To build systems that exhibit intelligent behaviour
To understand intelligence in order to model it

A Brief History of AI
In 1955, Newell and Simon created the first AI program. The person who finally coined the term artificial intelligence and is regarded as the father of AI is John McCarthy.

Applications of AI

1) Faster web searching
2) Work in deadly environments like extreme weather
3) Real-time language translate
4) Delivering a correct medical diagnosis
5) Intelligent tutoring systems in education
6) Algorithmic trading in share market
7) Quick market analysis and data mining
8) Portfolio management
9) Human resources and recruiting(HRM) – screeing resumes and performance appraisals.
10) News, publishing and writing in media
11) Online and customer service
12) Self-parking and advanced cruise controls in cars and other vehicles.
13) Optical character recognition (OCR)
14) Robotics
15) Hybrid intelligent system

What is the programming language used for artificial intelligence and machine learning?
As it purely depends on what languages you like programming in. AI programs have been written in just about every language ever created.

The most common programming languages are.

• Lisp,
• Prolog
• C/C++
• Java (recently)
• Python(more recently).

You can also read on AngularJS here

The post Artificial Intelligence appeared first on .