myawesomepkg 0.1.8__py3-none-any.whl

myawesomepkg/TSAPY1/p8_2_naive_bayes_document_classifier.py

@@ -0,0 +1,111 @@
+# -*- coding: utf-8 -*-
+"""P8-2 Naive Bayes Document Classifier.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1R4hGEod7Xzfmett09KGokYk375k1xX5W
+"""
+
+import pandas as pd
+
+msg=pd.read_excel('/content/naivetext.xlsx')
+msg
+
+print('The dimensions of the dataset',msg.shape)
+
+msg['labelnum']=msg.label.map({'pos':1,'neg':0})
+X=msg.message
+y=msg.labelnum
+print(X)
+print(y)
+
+#splitting the dataset into train and test data
+from sklearn.model_selection import train_test_split
+xtrain,xtest,ytrain,ytest=train_test_split(X,y)
+
+print ('\n The total number of Training Data :',ytrain.shape)
+
+print ('\n The total number of Test Data :',ytest.shape)
+
+#output of count vectoriser is a sparse matrix
+
+from sklearn.feature_extraction.text import CountVectorizer
+count_vect = CountVectorizer()
+xtrain_dtm = count_vect.fit_transform(xtrain)
+xtest_dtm=count_vect.transform(xtest)
+print('\n The words or Tokens in the text documents \n',count_vect.get_feature_names_out())
+
+df = pd.DataFrame(xtrain_dtm.toarray(), columns=count_vect.get_feature_names_out())
+
+# Training Naive Bayes (NB) classifier on training data
+from sklearn.naive_bayes import MultinomialNB
+
+clf = MultinomialNB().fit(xtrain_dtm,ytrain)
+predicted = clf.predict(xtest_dtm)
+
+#printing accuracy, Confusion matrix, Precision and Recall
+from sklearn import metrics
+print('\n Accuracy of the classifer is ', metrics.accuracy_score(ytest,predicted))
+
+#Checking the prediction made
+print(xtest)
+print(predicted)
+
+print('\n Confusion matrix\n', metrics.confusion_matrix(ytest,predicted))
+print('\n The value of Recall' ,
+metrics.recall_score(ytest,predicted))
+
+# Simple Naive Bayes Text Classifier
+
+
+
+# my code+++++++++++++++++++
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn import metrics
+
+# Load dataset
+data = pd.read_excel("/content/naivetext.xlsx")
+print("Dataset Loaded Successfully!")
+print("Shape of Dataset:", data.shape)
+
+# Convert labels to numbers (pos = 1, neg = 0)
+data['labelnum'] = data['label'].map({'pos': 1, 'neg': 0})
+
+# Split input (X) and output (y)
+X = data['message']
+y = data['labelnum']
+
+# Split data into training and testing
+x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
+print("\nTraining Samples:", len(x_train))
+print("Testing Samples:", len(x_test))
+
+# Convert text into numeric features
+vectorizer = CountVectorizer()
+x_train_dtm = vectorizer.fit_transform(x_train)
+x_test_dtm = vectorizer.transform(x_test)
+
+print("\nWords (Tokens):")
+print(vectorizer.get_feature_names_out())
+
+# Train Naive Bayes model
+model = MultinomialNB()
+model.fit(x_train_dtm, y_train)
+
+# Predict on test data
+y_pred = model.predict(x_test_dtm)
+
+# Show results
+print("\nAccuracy:", metrics.accuracy_score(y_test, y_pred))
+print("\nConfusion Matrix:\n", metrics.confusion_matrix(y_test, y_pred))
+print("\nRecall:", metrics.recall_score(y_test, y_pred))
+
+# Check few predictions
+print("\nSample Predictions:")
+for msg, pred in zip(x_test[:5], y_pred[:5]):
+    print(f"Message: {msg} --> Predicted Label: {'pos' if pred == 1 else 'neg'}")
+

myawesomepkg/TSAPY1/p9_1bayesian_network.py

@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+"""P9-1Bayesian Network.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1K14g_pZINxfYSFzX4UtRfyawHgOG9TI1
+"""
+
+pip install pgmpy
+
+import numpy as np
+import csv
+import pandas as pd
+from pgmpy.models import BayesianNetwork
+from pgmpy.estimators import MaximumLikelihoodEstimator
+from pgmpy.inference import VariableElimination
+
+#read Cleveland Heart Disease data
+heartDisease = pd.read_csv('/content/heart (1).csv')
+heartDisease = heartDisease.replace('?',np.nan)
+
+#display the data
+print('Few examples from the dataset are given below')
+print(heartDisease.head())
+
+#Model Bayesian Network
+#ImportError: BayesianNetwork has been deprecated. Please use DiscreteBayesianNetwork instead.
+
+model=DiscreteBayesianNetwork([('age','target'),('sex','target'),
+                       ('exang','target'),('cp','target'),
+                       ('target','restecg'),('target','chol')])
+
+#Learning CPDs using Maximum Likelihood Estimators
+print('\n Learning CPD using Maximum likelihood estimators')
+model.fit(heartDisease,estimator=MaximumLikelihoodEstimator)
+
+# Inferencing with Bayesian Network
+print('\n Inferencing with Bayesian Network:')
+HeartDisease_infer = VariableElimination(model)
+
+#computing the Probability of RestEcg given HeartDisease is present
+print('\n 1. Probability of HeartDisease given RestEcg')
+q=HeartDisease_infer.query(variables=['restecg'],evidence ={'target':1}, joint=False)
+print(q['restecg'])
+
+#computing the Probability of HeartDisease given Chestpain
+print('\n 2. Probability of HeartDisease given Chestpain')
+q=HeartDisease_infer.query(variables=['target'],evidence ={'cp':3}, joint=False)
+print(q['target'])
+
+import pandas as pd
+import numpy as np
+from pgmpy.models import DiscreteBayesianNetwork
+from pgmpy.estimators import MaximumLikelihoodEstimator
+from pgmpy.inference import VariableElimination
+
+# Load dataset
+data = pd.read_csv('/content/heart (1).csv')
+data = data.replace('?', np.nan)
+
+print("Sample data:")
+print(data.head())
+
+# Define the Bayesian Network structure using DiscreteBayesianNetwork
+model = DiscreteBayesianNetwork([
+    ('age', 'target'),
+    ('sex', 'target'),
+    ('exang', 'target'),
+    ('cp', 'target'),
+    ('target', 'restecg'),
+    ('target', 'chol')
+])
+
+# Fit the model
+model.fit(data, estimator=MaximumLikelihoodEstimator)
+print("\nModel training complete using Maximum Likelihood Estimation")
+
+# Inference
+infer = VariableElimination(model)
+
+# Query 1: Probability of RestEcg given HeartDisease
+print("\n1. Probability of RestEcg given HeartDisease:")
+q1 = infer.query(variables=['restecg'], evidence={'target': 1})
+print(q1)
+
+# Query 2: Probability of HeartDisease given Chest Pain (cp=3)
+print("\n2. Probability of HeartDisease given Chest Pain:")
+q2 = infer.query(variables=['target'], evidence={'cp': 3})
+print(q2)
+

myawesomepkg/TSAPY1/p9_b_loess_regression.py

@@ -0,0 +1,113 @@
+# -*- coding: utf-8 -*-
+"""P9-B-Loess Regression.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1acJ-zD2I0flDn0hYujYD4B6NI2hEALAS
+"""
+
+import matplotlib.pyplot as plt
+import pandas as pd
+import numpy as np
+def kernel(point, xmat, k):
+    m,n = np.shape(xmat)
+    weights = np.asmatrix(np.eye((m)))
+    for j in range(m):
+        diff = point - xmat[j]
+        weights[j,j] = np.exp(diff*diff.T/(-2.0*k**2))
+    return weights
+
+def localWeight(point, xmat, ymat, k):
+    wei = kernel(point,xmat,k)
+    W = (xmat.T*(wei*xmat)).I*(xmat.T*(wei*ymat.T))
+    return W
+
+def localWeightRegression(xmat, ymat, k):
+    m,n = np.shape(xmat) #Determine the dimensions of xmat(X)
+    ypred = np.zeros(m) #Set ypred
+    for i in range(m):
+        ypred[i] = xmat[i]*localWeight(xmat[i],xmat,ymat,k)
+    return ypred
+
+# load data points
+data = pd.read_csv('/content/10-dataset.csv')
+bill = np.array(data.total_bill)
+tip = np.array(data.tip)
+
+#`np.mat` was removed in the NumPy 2.0 release. Use `np.asmatrix` instead.
+
+#preparing and add 1 in bill
+mbill = np.asmatrix(bill)
+mtip = np.asmatrix(tip)
+
+m= np.shape(mbill)[1]
+one = np.asmatrix(np.ones(m))
+X = np.hstack((one.T,mbill.T))
+
+#set k here
+ypred = localWeightRegression(X,mtip,0.4)
+SortIndex = X[:,1].argsort(0)
+xsort = X[SortIndex][:,0]
+
+fig = plt.figure()
+ax = fig.add_subplot(1,1,1)
+ax.scatter(bill,tip, color='green')
+ax.plot(xsort[:,1],ypred[SortIndex], color = 'red', linewidth=5)
+plt.xlabel('Total bill')
+plt.ylabel('Tip')
+plt.show();
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# Load dataset
+data = pd.read_csv('/content/10-dataset.csv')
+bill = data['total_bill'].values
+tip = data['tip'].values
+
+# Prepare X matrix with intercept term
+X = np.column_stack((np.ones(len(bill)), bill))
+y = tip.reshape(-1, 1)
+
+# Gaussian Kernel function to calculate weights
+def kernel(point, X, k):
+    m = X.shape[0]
+    W = np.eye(m)
+    for i in range(m):
+        diff = point - X[i]
+        W[i,i] = np.exp(-(diff @ diff.T) / (2 * k**2))
+    return W
+
+# Calculate weights and regression coefficients for a point
+def lwlr_point(point, X, y, k):
+    W = kernel(point, X, k)
+    theta = np.linalg.inv(X.T @ W @ X) @ (X.T @ W @ y)
+    return point @ theta
+
+# Predict for all points
+def lwlr(X, y, k):
+    y_pred = np.zeros(len(X))
+    for i in range(len(X)):
+        y_pred[i] = lwlr_point(X[i], X, y, k)
+    return y_pred
+
+# Apply LWLR with bandwidth k=0.4
+k = 0.4
+y_pred = lwlr(X, y, k)
+
+# Sort X for plotting smooth curve
+sort_idx = X[:,1].argsort()
+X_sorted = X[sort_idx]
+y_pred_sorted = y_pred[sort_idx]
+
+# Plot results
+plt.scatter(bill, tip, color='green', label='Data points')
+plt.plot(X_sorted[:,1], y_pred_sorted, color='red', linewidth=2, label='LWLR fit')
+plt.xlabel('Total bill')
+plt.ylabel('Tip')
+plt.title('Locally Weighted Linear Regression')
+plt.legend()
+plt.show()
+

myawesomepkg/TSAPY1/p_1_test_and_train.py

@@ -0,0 +1,98 @@
+# -*- coding: utf-8 -*-
+"""P-1_test and train.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/14lT2R6bt-YH_7p_1kdPFnVQ3YIIiaBLJ
+"""
+
+#Design a simple machine learning model to train the training instances and test the same
+import pandas as pd
+import matplotlib.pyplot as plt
+df = pd.read_csv("/content/Cars.csv") #Read data
+df.head()
+
+plt.scatter(df['Milage'],df['Sell Price']) #Plot to compare Milage(Independant variable) with Sell Price(Dependant variable)
+plt.show()
+plt.scatter(df['Age'],df['Sell Price'])#Plot to compare Age(Independant variable) with Sell Price(Dependant variable)
+plt.show()
+X = df[['Milage','Age']] #Determine X
+Y = df['Sell Price']    # Determine Y
+X #Display X
+Y #Display Y
+from sklearn.model_selection import train_test_split
+X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.2)#Create a training set and testing set
+len(X_train)
+len(X_test)
+from sklearn.linear_model import LinearRegression
+clf = LinearRegression()
+clf.fit(X_train,Y_train) # Train the model
+clf.predict(X_test) # Use the rained model to predict the testing set
+clf.score(X_test,Y_test) #Calculate the accuracy
+
+# my coode
+
+# Importing necessary libraries
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error
+
+# Load dataset
+df = pd.read_csv(r"/content/Cars.csv")  # Use raw string for Windows path
+print("✅ Data Loaded Successfully!")
+print(df.head())
+
+# Data visualization
+plt.figure(figsize=(10,4))
+plt.subplot(1,2,1)
+plt.scatter(df['Milage'], df['Sell Price'], color='blue')
+plt.title('Milage vs Sell Price')
+plt.xlabel('Milage')
+plt.ylabel('Sell Price')
+
+plt.subplot(1,2,2)
+plt.scatter(df['Age'], df['Sell Price'], color='green')
+plt.title('Age vs Sell Price')
+plt.xlabel('Age')
+plt.ylabel('Sell Price')
+
+plt.tight_layout()
+plt.show()
+
+# Features (X) and Target (Y)
+X = df[['Milage', 'Age']]
+Y = df['Sell Price']
+
+# Splitting data into training and testing sets (80% train, 20% test)
+X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)
+
+# Create and train the Linear Regression model
+model = LinearRegression()
+model.fit(X_train, Y_train)
+
+# Predict the test set results
+Y_pred = model.predict(X_test)
+
+# Evaluate the model
+r2 = r2_score(Y_test, Y_pred)
+mae = mean_absolute_error(Y_test, Y_pred)
+mse = mean_squared_error(Y_test, Y_pred)
+
+# Display metrics
+print("\n📊 Model Evaluation Metrics:")
+print(f"R² Score (Accuracy): {r2:.4f}")
+print(f"Mean Absolute Error: {mae:.2f}")
+print(f"Mean Squared Error: {mse:.2f}")
+
+# Compare actual vs predicted values visually
+plt.figure(figsize=(6,4))
+plt.scatter(Y_test, Y_pred, color='purple')
+plt.xlabel('Actual Sell Price')
+plt.ylabel('Predicted Sell Price')
+plt.title('Actual vs Predicted Sell Price')
+plt.grid(True)
+plt.show()
+