💡 Keras: Building Neural Networks Simply

Keras is a high-level deep learning API, now part of TensorFlow, designed for fast and easy experimentation. This guide covers the fundamental workflow: defining, compiling, training, and using a neural network model.

from tensorflow import keras
from tensorflow.keras import layers

# Define a Sequential model
model = keras.Sequential([
    # Input layer with 64 neurons, expecting flat input data
    layers.Dense(64, activation="relu", input_shape=(784,)),
    # A hidden layer with 32 neurons
    layers.Dense(32, activation="relu"),
    # Output layer with 10 neurons for 10-class classification
    layers.Dense(10, activation="softmax")
])

model.summary()

• Model Definition: keras.Sequential creates a simple, layer-by-layer model.
• layers.Dense is a standard fully-connected layer. The first layer must specify the input_shape.
• activation functions like "relu" introduce non-linearity, while "softmax" is used on the output layer for multi-class classification to produce probabilities.

# (Continuing from the previous step)
model.compile(
    optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metrics=['accuracy']
)

print("Model compiled successfully.")

• Compilation: .compile() configures the model for training.
• optimizer is the algorithm used to update the model's weights (e.g., 'adam' is a popular choice).
• loss is the function the model tries to minimize during training. sparse_categorical_crossentropy is common for integer-based classification labels.
• metrics are used to monitor the training and testing steps. Here, we track accuracy.

import numpy as np

# Create dummy training data
x_train = np.random.random((1000, 784))
y_train = np.random.randint(10, size=(1000,))

# Train the model
history = model.fit(
    x_train,
    y_train,
    epochs=5,
    batch_size=32,
    verbose=0 # Hides the progress bar for a cleaner output
)

print(f"Training complete. Final accuracy: {history.history['accuracy'][-1]:.4f}")
# Output (will vary):
# Training complete. Final accuracy: 0.4570

• Training: The .fit() method trains the model on your data.
• x_train and y_train are your input features and target labels.
• epochs defines how many times the model will see the entire dataset.
• batch_size is the number of samples processed before the model is updated.

# Create a single dummy sample to test
x_test = np.random.random((1, 784))

# Get the model's prediction
predictions = model.predict(x_test)
predicted_class = np.argmax(predictions[0])

print(f"Predicted class: {predicted_class}")
print(f"Confidence scores: {predictions[0].round(2)}")
# Output (will vary):
# Predicted class: 3
# Confidence scores: [0.09 0.1  0.1  0.12 0.1  0.09 0.11 0.1  0.09 0.1 ]

• Prediction: .predict() is used to make predictions on new, unseen data.
• For a classification model with a softmax output, this returns an array of probabilities for each class.
• np.argmax() is used to find the index (the class) with the highest probability score.

#Keras #TensorFlow #DeepLearning #MachineLearning #Python

━━━━━━━━━━━━━━━
By: @CodeProgrammer ✨

💡 {{Python Exam}}

Python dictionaries are a fundamental data structure used to store data as key-value pairs. They are mutable (can be changed), dynamic, and since Python 3.7, they maintain the order of insertion. Keys must be unique and of an immutable type (like strings or numbers), while values can be of any type.

1. Creating and Accessing Dictionaries

# Creating a dictionary
student = {
    "name": "Alex",
    "age": 21,
    "courses": ["Math", "CompSci"]
}

# Accessing values
print(f"Name: {student['name']}")
print(f"Age: {student.get('age')}")

# Safe access for a non-existent key
print(f"Major: {student.get('major', 'Not specified')}")

# --- Sample Output ---
# Name: Alex
# Age: 21
# Major: Not specified

• A dictionary is created using curly braces {} with key: value pairs.
• student['name'] accesses the value using its key. This will raise a KeyError if the key doesn't exist.
• student.get('age') is a safer way to access a value, returning None if the key is not found.
• .get() can also take a second argument as a default value to return if the key is missing.

2. Modifying a Dictionary

user_profile = {
    "username": "coder_01",
    "level": 5
}

# Add a new key-value pair
user_profile["email"] = "coder@example.com"
print(f"After adding: {user_profile}")

# Update an existing value
user_profile["level"] = 6
print(f"After updating: {user_profile}")

# Remove a key-value pair
del user_profile["email"]
print(f"After deleting: {user_profile}")

# --- Sample Output ---
# After adding: {'username': 'coder_01', 'level': 5, 'email': 'coder@example.com'}
# After updating: {'username': 'coder_01', 'level': 6, 'email': 'coder@example.com'}
# After deleting: {'username': 'coder_01', 'level': 6}

• A new key-value pair is added using simple assignment dict[new_key] = new_value.
• The value of an existing key is updated by assigning a new value to it.
• The del keyword completely removes a key-value pair from the dictionary.

3. Looping Through Dictionaries

inventory = {
    "apples": 430,
    "bananas": 312,
    "oranges": 525
}

# Loop through keys
print("--- Keys ---")
for item in inventory.keys():
    print(item)

# Loop through values
print("\n--- Values ---")
for quantity in inventory.values():
    print(quantity)

# Loop through key-value pairs
print("\n--- Items ---")
for item, quantity in inventory.items():
    print(f"{item}: {quantity}")

# --- Sample Output ---
# --- Keys ---
# apples
# bananas
# oranges
#
# --- Values ---
# 430
# 312
# 525
#
# --- Items ---
# apples: 430
# bananas: 312
# oranges: 525

• .keys() returns a view object of all keys, which can be looped over.
• .values() returns a view object of all values.
• .items() returns a view object of key-value tuple pairs, allowing you to easily access both in each loop iteration.

#Python #DataStructures #Dictionaries #Programming #PythonBasics

━━━━━━━━━━━━━━━
By: @CodeProgrammer ✨

#NLP #Lesson #SentimentAnalysis #MachineLearning

Building an NLP Model from Scratch: Sentiment Analysis

This lesson will guide you through creating a complete Natural Language Processing (NLP) project. We will build a sentiment analysis classifier that can determine if a piece of text is positive or negative.

---

Step 1: Setup and Data Preparation

First, we need to import the necessary libraries and prepare our dataset. For simplicity, we'll use a small, hard-coded list of sentences. In a real-world project, you would load this data from a file (e.g., a CSV).

#Python #DataPreparation

# Imports and Data
import re
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, classification_report
import nltk
from nltk.corpus import stopwords

# You may need to download stopwords for the first time
# nltk.download('stopwords')

# Sample Data (In a real project, load this from a file)
texts = [
    "I love this movie, it's fantastic!",
    "This was a terrible film.",
    "The acting was superb and the plot was great.",
    "I would not recommend this to anyone.",
    "It was an okay movie, not the best but enjoyable.",
    "Absolutely brilliant, a must-see!",
    "A complete waste of time and money.",
    "The story was compelling and engaging."
]
# Labels: 1 for Positive, 0 for Negative
labels = [1, 0, 1, 0, 1, 1, 0, 1]

---

Step 2: Text Preprocessing

Computers don't understand words, so we must clean and process our text data first. This involves making text lowercase, removing punctuation, and filtering out common "stop words" (like 'the', 'a', 'is') that don't add much meaning.

#TextPreprocessing #DataCleaning

# Text Preprocessing Function
stop_words = set(stopwords.words('english'))

def preprocess_text(text):
    # Make text lowercase
    text = text.lower()
    # Remove punctuation
    text = re.sub(r'[^\w\s]', '', text)
    # Tokenize and remove stopwords
    tokens = text.split()
    filtered_tokens = [word for word in tokens if word not in stop_words]
    return " ".join(filtered_tokens)

# Apply preprocessing to our dataset
processed_texts = [preprocess_text(text) for text in texts]
print("--- Original vs. Processed ---")
for i in range(3):
    print(f"Original: {texts[i]}")
    print(f"Processed: {processed_texts[i]}\n")

---

Step 3: Splitting the Data

We must split our data into a training set (to teach the model) and a testing set (to evaluate its performance on unseen data).

#MachineLearning #TrainTestSplit

# Splitting data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(
    processed_texts, 
    labels, 
    test_size=0.25, # Use 25% of data for testing
    random_state=42 # for reproducibility
)

print(f"Training samples: {len(X_train)}")
print(f"Testing samples: {len(X_test)}")

---

Step 4: Feature Extraction (Vectorization)

We need to convert our cleaned text into a numerical format. We'll use TF-IDF (Term Frequency-Inverse Document Frequency). This technique converts text into vectors of numbers, giving more weight to words that are important to a document but not common across all documents.

#FeatureEngineering #TFIDF #Vectorization

#YOLOv8 #ComputerVision #TrafficManagement #Python #AI #SmartCity

Lesson: Detecting Traffic Congestion in Road Lanes with YOLOv8

This tutorial will guide you through building a system to monitor traffic on a highway from a video feed. We'll use YOLOv8 to detect vehicles and then define specific zones (lanes) to count the number of vehicles within them, determining if a lane is congested.

---

#Step 1: Project Setup and Dependencies

We need to install ultralytics for YOLOv8 and opencv-python for video and image processing. numpy is also essential for handling the coordinates of our detection zones.

pip install ultralytics opencv-python numpy

Create a Python script (e.g., traffic_monitor.py) and import the necessary libraries.

import cv2
import numpy as np
from ultralytics import YOLO

# Hashtags: #Setup #Python #OpenCV #YOLOv8

---

#Step 2: Model Loading and Lane Definition

We'll load a pre-trained YOLOv8 model, which is excellent at detecting common objects like cars, trucks, and buses. The most critical part of this step is defining the zones of interest (our lanes) as polygons on the video frame. You will need to adjust these coordinates to match the perspective of your specific video.

You will also need a video file, for example, traffic_video.mp4.

# Load a pre-trained YOLOv8 model (yolov8n.pt is small and fast)
model = YOLO('yolov8n.pt')

# Path to your video file
VIDEO_PATH = 'traffic_video.mp4'

# Define the polygons for two lanes.
# IMPORTANT: You MUST adjust these coordinates for your video's perspective.
# Each polygon is a numpy array of [x, y] coordinates.
LANE_1_POLYGON = np.array([[20, 400], [450, 400], [450, 250], [20, 250]], np.int32)
LANE_2_POLYGON = np.array([[500, 400], [980, 400], [980, 250], [500, 250]], np.int32)

# Define the congestion threshold. If vehicle count > this, the lane is congested.
CONGESTION_THRESHOLD = 10

# Hashtags: #Configuration #AIModel #SmartCity

---

#Step 3: Main Loop for Detection and Counting

This is the core of our program. We will loop through each frame of the video, run vehicle detection, and then check if the center of each detected vehicle falls inside our predefined lane polygons. We will keep a count for each lane.

cap = cv2.VideoCapture(VIDEO_PATH)

while cap.isOpened():
    success, frame = cap.read()
    if not success:
        break

    # Run YOLOv8 inference on the frame
    results = model(frame)

    # Initialize vehicle counts for each lane for the current frame
    lane_1_count = 0
    lane_2_count = 0

    # Process detection results
    for r in results:
        for box in r.boxes:
            # Check if the detected object is a vehicle
            class_id = int(box.cls[0])
            class_name = model.names[class_id]
            
            if class_name in ['car', 'truck', 'bus', 'motorbike']:
                # Get bounding box coordinates
                x1, y1, x2, y2 = map(int, box.xyxy[0])
                
                # Calculate the center point of the bounding box
                center_x = (x1 + x2) // 2
                center_y = (y1 + y2) // 2

                # Check if the center point is inside Lane 1
                if cv2.pointPolygonTest(LANE_1_POLYGON, (center_x, center_y), False) >= 0:
                    lane_1_count += 1
                
                # Check if the center point is inside Lane 2
                elif cv2.pointPolygonTest(LANE_2_POLYGON, (center_x, center_y), False) >= 0:
                    lane_2_count += 1

# Hashtags: #RealTime #ObjectDetection #VideoProcessing

(Note: The code below should be placed inside the while loop of Step 3)

---

#Step 4: Visualization and Displaying Results