myawesomepkg 0.1.8__py3-none-any.whl

myawesomepkg/TSAPY1/p1_2_pca_iris.py

@@ -0,0 +1,141 @@
+# -*- coding: utf-8 -*-
+"""P1-2-PCA Iris.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1PyEQgfiZYSfkl9j1bYi61d2LQwF86D3U
+"""
+
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+
+def PCA(X , num_components):
+
+    #Step-1
+    # X_meaned = X - np.mean(X , axis = 0)
+    X_meaned = sc.fit_transform(X)
+
+    #Step-2
+    cov_mat = np.cov(X_meaned , rowvar = False)
+
+    #Step-3
+    eigen_values , eigen_vectors = np.linalg.eigh(cov_mat)
+
+    #Step-4
+    sorted_index = np.argsort(eigen_values)[::-1]
+    sorted_eigenvalue = eigen_values[sorted_index]
+    sorted_eigenvectors = eigen_vectors[:,sorted_index]
+
+    #Step-5
+    eigenvector_subset = sorted_eigenvectors[:,0:num_components]
+
+    #Step-6
+    X_reduced = np.dot(eigenvector_subset.transpose() , X_meaned.transpose() ).transpose()
+
+    return X_reduced
+
+data = pd.read_csv("/content/iris.csv")
+data.head()
+
+#prepare the data
+x = data.iloc[:,0:4]
+
+#prepare the target
+target = data.iloc[:,4]
+
+x.head()
+
+target.head()
+
+#Applying it to PCA function
+mat_reduced = PCA(x , 2)
+
+#Creating a Pandas DataFrame of reduced Dataset
+principal_df = pd.DataFrame(mat_reduced , columns = ['PC1','PC2'])
+
+#Display the Principal Coponents
+principal_df.head()
+
+#Concat it with target variable to create a complete Dataset
+principal_df = pd.concat([principal_df , pd.DataFrame(target)] , axis = 1)
+
+principal_df.head()
+
+import seaborn as sb
+import matplotlib.pyplot as plt
+
+plt.figure(figsize = (6,6))
+sb.scatterplot(data = principal_df , x = 'PC1', y = 'PC2' , hue = "variety" , s = 60 , palette= 'icefire')
+#sb.scatterplot(data = principal_df , x = 'PC1', y = 'PC2', s = 60 , palette= 'icefire')
+
+#my coooode
+
+# Import necessary libraries
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.preprocessing import StandardScaler
+
+# Initialize scaler
+scaler = StandardScaler()
+
+# Define PCA function
+def PCA(X, num_components):
+    # Step 1: Standardize the dataset
+    X_scaled = scaler.fit_transform(X)
+
+    # Step 2: Compute covariance matrix
+    covariance_matrix = np.cov(X_scaled, rowvar=False)
+
+    # Step 3: Compute eigenvalues and eigenvectors
+    eigen_values, eigen_vectors = np.linalg.eigh(covariance_matrix)
+
+    # Step 4: Sort eigenvalues and eigenvectors in descending order
+    sorted_indices = np.argsort(eigen_values)[::-1]
+    eigen_values = eigen_values[sorted_indices]
+    eigen_vectors = eigen_vectors[:, sorted_indices]
+
+    # Step 5: Select top components
+    eigenvector_subset = eigen_vectors[:, :num_components]
+
+    # Step 6: Project data onto principal components
+    X_reduced = np.dot(X_scaled, eigenvector_subset)
+
+    return X_reduced, eigen_values
+
+# Load dataset
+data = pd.read_csv(r"/content/iris.csv")
+
+# Separate features and target
+X = data.iloc[:, :-1]
+y = data.iloc[:, -1]
+
+# Apply PCA
+X_reduced, eigen_values = PCA(X, 2)
+
+# Create a DataFrame with principal components
+pca_df = pd.DataFrame(X_reduced, columns=['PC1', 'PC2'])
+pca_df['Variety'] = y
+
+# Display first few rows
+print(pca_df.head())
+
+# Variance explained by each component
+explained_variance = (eigen_values / np.sum(eigen_values)) * 100
+print("\nExplained Variance (%):")
+print(explained_variance[:2])
+
+# Visualization
+plt.figure(figsize=(7, 6))
+sns.scatterplot(data=pca_df, x='PC1', y='PC2', hue='Variety', s=80, palette='viridis')
+plt.title('PCA on Iris Dataset', fontsize=14)
+plt.xlabel(f'PC1 ({explained_variance[0]:.2f}% variance)')
+plt.ylabel(f'PC2 ({explained_variance[1]:.2f}% variance)')
+plt.legend(title='Variety')
+plt.grid(True, linestyle='--', alpha=0.6)
+plt.show()
+

myawesomepkg/TSAPY1/p2_1_find_s.py

@@ -0,0 +1,78 @@
+# -*- coding: utf-8 -*-
+"""P2-1 Find-S.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1f8yD_lr15trt6SrY0k7GkzBGPc-iHKDR
+"""
+
+import pandas as pd
+import numpy as np
+
+data = pd.read_csv('/content/lab1.csv')
+data
+
+concepts = np.array(data)[:,:-1]
+concepts
+
+target = np.array(data)[:,-1]
+target
+
+def train(con,tar):
+	for i,val in enumerate(tar):
+		if val == 'yes':
+			specific_h = con[i].copy()
+			break
+	for i,val in enumerate(con):
+		if tar[i] == 'yes':
+			for x in range(len(specific_h)):
+				if val[x] != specific_h[x]:
+					specific_h[x] = '?'
+				else:
+					pass
+	return specific_h
+
+print(train(concepts,target))
+
+# my code
+
+# ✅ Improved FIND-S Algorithm Implementation
+
+import pandas as pd
+import numpy as np
+
+# Load dataset
+data = pd.read_csv(r"/content/lab1.csv")
+
+# Display the data
+print("Dataset:\n", data, "\n")
+
+# Separate features (concepts) and target
+concepts = data.iloc[:, :-1].values
+target = data.iloc[:, -1].values
+
+# FIND-S algorithm definition
+def find_s(concepts, target):
+    # Step 1: Initialize specific hypothesis with the first positive example
+    specific_h = None
+    for i, val in enumerate(target):
+        if val.lower() == 'yes':
+            specific_h = concepts[i].copy()
+            break
+
+    # Step 2: Generalize only when necessary
+    for i, val in enumerate(target):
+        if val.lower() == 'yes':
+            for j in range(len(specific_h)):
+                if concepts[i][j] != specific_h[j]:
+                    specific_h[j] = '?'
+
+    return specific_h
+
+# Train the model
+final_hypothesis = find_s(concepts, target)
+
+# Display results
+print("✅ Final Specific Hypothesis:\n", final_hypothesis)
+

myawesomepkg/TSAPY1/p2_bcandidate_elimination_algorithm_(1).py

@@ -0,0 +1,85 @@
+# -*- coding: utf-8 -*-
+"""P2-BCandidate Elimination algorithm (1).ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1J2QTr3esKQiO5tSmwN9heAyTb86Lzh7f
+"""
+
+import numpy as np
+import pandas as pd
+
+data = pd.read_csv('/content/enjoysport.csv')
+data
+
+concepts = np.array(data.iloc[:,0:-1])
+print("\nInstances are:\n",concepts)
+target = np.array(data.iloc[:,-1])
+print("\nTarget Values are: ",target)
+
+def learn(concepts, target):
+    specific_h = concepts[0].copy()
+    print("\nInitialization of specific_h and genearal_h")
+    print("\nSpecific Boundary: ", specific_h)
+    general_h = [["?" for i in range(len(specific_h))] for i in range(len(specific_h))]
+    print("\nGeneric Boundary: ",general_h)
+
+    for i, h in enumerate(concepts):
+        print("\nInstance", i+1 , "is ", h)
+        if target[i] == "yes":
+            print("Instance is Positive ")
+            for x in range(len(specific_h)):
+                if h[x]!= specific_h[x]:
+                    specific_h[x] ='?'
+                    general_h[x][x] ='?'
+
+        if target[i] == "no":
+            print("Instance is Negative ")
+            for x in range(len(specific_h)):
+                if h[x]!= specific_h[x]:
+                    general_h[x][x] = specific_h[x]
+                else:
+                    general_h[x][x] = '?'
+
+        print("Specific Bundary after ", i+1, "Instance is ", specific_h)
+        print("Generic Boundary after ", i+1, "Instance is ", general_h)
+        print("\n")
+
+    indices = [i for i, val in enumerate(general_h) if val == ['?', '?', '?', '?', '?', '?']]
+
+    for i in indices:
+        general_h.remove(['?', '?', '?', '?', '?', '?'])
+    return specific_h, general_h
+
+s_final, g_final = learn(concepts, target)
+print("Final Specific_h:", s_final, sep="\n")
+print("Final General_h:", g_final, sep="\n")
+
+#my coode
+
+import pandas as pd
+import numpy as np
+
+# Load dataset
+data = pd.read_csv(r'/content/enjoysport.csv')
+
+# Split into features and target
+concepts = np.array(data.iloc[:, :-1])
+target = np.array(data.iloc[:, -1])
+
+def find_s(concepts, target):
+    for i, val in enumerate(target):
+        if val.lower() == 'yes':
+            specific_h = concepts[i].copy()
+            break
+
+    for i, val in enumerate(concepts):
+        if target[i].lower() == 'yes':
+            for x in range(len(specific_h)):
+                if val[x] != specific_h[x]:
+                    specific_h[x] = '?'
+    return specific_h
+
+print("Most specific hypothesis:", find_s(concepts, target))
+

myawesomepkg/TSAPY1/p3_1_least_square_regression.py

@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+"""P3-1-Least Square Regression.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1gU6rRYa8vNSqSFvH9dDuRKc80I1Oejvg
+"""
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+plt.rcParams['figure.figsize'] = (12.0, 9.0)
+
+# Preprocessing Input data
+data = pd.read_csv('/content/Data (2).csv')
+X = data.iloc[:, 0]
+Y = data.iloc[:, 1]
+plt.scatter(X, Y)
+plt.show()
+
+# Building the model
+#Calculating the means
+X_mean = np.mean(X)
+Y_mean = np.mean(Y)
+
+cov = 0
+var = 0
+for i in range(len(X)):
+    cov += (X[i] - X_mean)*(Y[i] - Y_mean)# Calculate the covariance of X and Y
+    var += (X[i] - X_mean)**2 # Calculate the variance of X
+regcoeff = cov / var
+intercept = Y_mean - regcoeff*X_mean
+
+print (regcoeff, intercept)
+
+# Making predictions
+Y_pred = regcoeff*X + intercept
+
+plt.scatter(X, Y) # actual
+plt.plot([min(X), max(X)], [min(Y_pred), max(Y_pred)], color='red') # predicted
+plt.show()
+
+# my cooode
+
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Set plot size
+plt.rcParams['figure.figsize'] = (10, 6)
+
+# Load data
+data = pd.read_csv(r'/content/Data (2).csv')
+
+# Extract features and target
+X = data.iloc[:, 0].values
+Y = data.iloc[:, 1].values
+
+# Scatter plot of original data
+plt.scatter(X, Y, color='blue', label='Actual Data')
+plt.title('Data Visualization')
+plt.xlabel('X')
+plt.ylabel('Y')
+plt.legend()
+plt.show()
+
+# --- Linear Regression from Scratch ---
+
+# Calculate means
+X_mean = np.mean(X)
+Y_mean = np.mean(Y)
+
+# Calculate covariance and variance
+cov = np.sum((X - X_mean) * (Y - Y_mean))
+var = np.sum((X - X_mean) ** 2)
+
+# Regression coefficients
+reg_coeff = cov / var
+intercept = Y_mean - reg_coeff * X_mean
+
+print(f"Slope (regression coefficient): {reg_coeff:.4f}")
+print(f"Intercept: {intercept:.4f}")
+
+# Predictions
+Y_pred = reg_coeff * X + intercept
+
+# --- Model Evaluation ---
+# R² Score
+ss_total = np.sum((Y - Y_mean) ** 2)
+ss_residual = np.sum((Y - Y_pred) ** 2)
+r2_score = 1 - (ss_residual / ss_total)
+print(f"R² Score: {r2_score:.4f}")
+
+# --- Visualization ---
+plt.scatter(X, Y, color='blue', label='Actual Data')
+plt.plot(X, Y_pred, color='red', label='Regression Line')
+plt.title('Simple Linear Regression')
+plt.xlabel('X')
+plt.ylabel('Y')
+plt.legend()
+plt.grid(True)
+plt.show()

myawesomepkg/TSAPY1/p3_2_logistic_regression_algorithm.py

@@ -0,0 +1,79 @@
+# -*- coding: utf-8 -*-
+"""P3-2-Logistic Regression algorithm.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1jJpY0R35HT2AXPM9yNTJwX6JqW5Q6Zta
+"""
+
+import pandas as pd
+from matplotlib import pyplot as plt
+df = pd.read_csv("/content/insurance_data.csv")
+df.head()
+plt.scatter(df.Age,df.have_insurance,marker='+',color='red')
+plt.show()
+from sklearn.model_selection import train_test_split
+X_train, X_test, Y_train, Y_test = train_test_split(df[['Age']],df.have_insurance,test_size=0.1)
+from sklearn.linear_model import LogisticRegression
+model = LogisticRegression()
+model.fit(X_train, Y_train)#Training the model
+model.predict(X_test)#Prediction on the test set
+model.score(X_test,Y_test)#Calculating the accuracy
+model.predict_proba(X_test)#Predicting the probabilities
+
+#my coode
+
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import confusion_matrix, classification_report, accuracy_score
+
+# Load dataset
+df = pd.read_csv(r'/content/insurance_data.csv')
+
+# Display first few rows
+print("Dataset Preview:\n", df.head())
+
+# Visualize the data
+plt.figure(figsize=(8, 5))
+plt.scatter(df['Age'], df['have_insurance'], marker='+', color='red')
+plt.title('Insurance Data Distribution')
+plt.xlabel('Age')
+plt.ylabel('Has Insurance (0 = No, 1 = Yes)')
+plt.grid(True)
+plt.show()
+
+# Split data into train and test
+X_train, X_test, y_train, y_test = train_test_split(
+    df[['Age']], df['have_insurance'], test_size=0.2, random_state=42
+)
+
+# Train Logistic Regression model
+model = LogisticRegression()
+model.fit(X_train, y_train)
+
+# Predictions
+y_pred = model.predict(X_test)
+y_prob = model.predict_proba(X_test)[:, 1]
+
+# Model evaluation
+accuracy = accuracy_score(y_test, y_pred)
+print(f"✅ Model Accuracy: {accuracy:.4f}\n")
+
+print("🔹 Classification Report:\n", classification_report(y_test, y_pred))
+print("🔹 Confusion Matrix:\n", confusion_matrix(y_test, y_pred))
+
+# Plot logistic curve
+plt.figure(figsize=(8, 5))
+plt.scatter(df['Age'], df['have_insurance'], color='blue', label='Actual Data')
+X_range = pd.DataFrame({'Age': range(int(df['Age'].min()), int(df['Age'].max()))})
+plt.plot(X_range, model.predict_proba(X_range)[:, 1], color='red', label='Logistic Curve')
+plt.title('Logistic Regression Fit')
+plt.xlabel('Age')
+plt.ylabel('Probability of Having Insurance')
+plt.legend()
+plt.grid(True)
+plt.show()
+

myawesomepkg/TSAPY1/p5_1_hierarchical_clustering.py

@@ -0,0 +1,143 @@
+# -*- coding: utf-8 -*-
+"""P5-1 Hierarchical Clustering.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1-t2ZOVavQ3YXZC9-s7tvo3uI0acgS2C5
+"""
+
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.cluster import AgglomerativeClustering
+from scipy.cluster import hierarchy
+
+#load the Penguins dataset
+data = pd.read_csv("/content/penguins.csv")
+data.head()
+
+data['species'].value_counts()
+
+print(data.shape) # (344, 9)
+
+#trimming the dataset to the chosen columns and dropping rows with missing data
+df = data[['bill_length_mm', 'flipper_length_mm']]
+df = df.dropna(axis=0)
+
+df.head()
+
+#use Scipy's hierarchy.linkage() to form clusters and plot them with hierarchy.dendrogram()
+
+clusters = hierarchy.linkage(df, method="ward")
+
+plt.figure(figsize=(8, 6))
+dendrogram = hierarchy.dendrogram(clusters)
+# Plotting a horizontal line based on the first biggest distance between clusters
+plt.axhline(150, color='red', linestyle='--');
+# Plotting a horizontal line based on the second biggest distance between clusters
+plt.axhline(100, color='crimson');
+
+#perform Agglomerative Clustering with Scikit-Learn to find cluster labels for the three types of penguins
+clustering_model = AgglomerativeClustering(n_clusters=3, linkage="ward")
+clustering_model.fit(df)
+labels = clustering_model.labels_
+
+#plot the data before and after Agglomerative Clustering with 3 clusters
+fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(15,5))
+sns.scatterplot(ax=axes[0], data=df, x='bill_length_mm', y='flipper_length_mm').set_title('Without cliustering')
+sns.scatterplot(ax=axes[1], data=df, x='bill_length_mm', y='flipper_length_mm', hue=clustering_model.labels_).set_title('With clustering');
+
+#Agglomerative Clustering without specifying the number of clusters
+clustering_model_no_clusters = AgglomerativeClustering(linkage="ward")
+clustering_model_no_clusters.fit(df)
+labels_no_clusters = clustering_model_no_clusters.labels_
+
+# plot the data without Agglomerative Clustering, with 3 clusters and with no pre defined clusters
+fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(15,5))
+sns.scatterplot(ax=axes[0], data=df, x='bill_length_mm', y='flipper_length_mm').set_title('Without cliustering')
+sns.scatterplot(ax=axes[1], data=df, x='bill_length_mm', y='flipper_length_mm', hue=clustering_model.labels_).set_title('With 3 clusters')
+sns.scatterplot(ax=axes[2], data=df, x='bill_length_mm', y='flipper_length_mm', hue=clustering_model_no_clusters.labels_).set_title('Without choosing number of clusters');
+
+# my cooode
+
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.cluster import AgglomerativeClustering
+from scipy.cluster import hierarchy
+
+# ============================
+# 1️⃣ Load & Prepare Dataset
+# ============================
+data = pd.read_csv("/content/penguins.csv")
+
+print("Dataset shape:", data.shape)
+print("\nSpecies count:\n", data['species'].value_counts())
+
+# Select relevant numerical features and drop missing rows
+df = data[['bill_length_mm', 'flipper_length_mm']].dropna()
+print("\nCleaned dataset shape:", df.shape)
+print(df.head())
+
+# ============================
+# 2️⃣ Create Dendrogram (Hierarchical Tree)
+# ============================
+plt.figure(figsize=(10, 6))
+clusters = hierarchy.linkage(df, method="ward")
+
+# Plot the dendrogram
+dendrogram = hierarchy.dendrogram(clusters, color_threshold=100)
+plt.axhline(150, color='red', linestyle='--', label='Threshold 150')
+plt.axhline(100, color='orange', linestyle='--', label='Threshold 100')
+plt.title("Hierarchical Clustering Dendrogram (Ward’s Method)")
+plt.xlabel("Data Points")
+plt.ylabel("Euclidean Distance")
+plt.legend()
+plt.grid(True)
+plt.show()
+
+# ============================
+# 3️⃣ Agglomerative Clustering (with 3 clusters)
+# ============================
+agg3 = AgglomerativeClustering(n_clusters=3, linkage="ward")
+labels_3 = agg3.fit_predict(df)
+
+# Add cluster labels to dataframe
+df['Cluster_3'] = labels_3
+
+# ============================
+# 4️⃣ Visualization — With and Without Clustering
+# ============================
+fig, axes = plt.subplots(1, 2, figsize=(14, 5))
+sns.scatterplot(ax=axes[0], data=df, x='bill_length_mm', y='flipper_length_mm', color='gray')
+axes[0].set_title("Without Clustering")
+
+sns.scatterplot(ax=axes[1], data=df, x='bill_length_mm', y='flipper_length_mm', hue='Cluster_3', palette='viridis', s=70)
+axes[1].set_title("With 3 Clusters")
+plt.tight_layout()
+plt.show()
+
+# ============================
+# 5️⃣ Agglomerative Clustering (without predefined clusters)
+# ============================
+agg_auto = AgglomerativeClustering(linkage="ward")
+labels_auto = agg_auto.fit_predict(df[['bill_length_mm', 'flipper_length_mm']])
+df['Cluster_auto'] = labels_auto
+
+# ============================
+# 6️⃣ Compare — No Clustering vs 3 Clusters vs Auto
+# ============================
+fig, axes = plt.subplots(1, 3, figsize=(18, 5))
+
+sns.scatterplot(ax=axes[0], data=df, x='bill_length_mm', y='flipper_length_mm', color='gray')
+axes[0].set_title("Without Clustering")
+
+sns.scatterplot(ax=axes[1], data=df, x='bill_length_mm', y='flipper_length_mm', hue='Cluster_3', palette='cool', s=70)
+axes[1].set_title("With 3 Clusters")
+
+sns.scatterplot(ax=axes[2], data=df, x='bill_length_mm', y='flipper_length_mm', hue='Cluster_auto', palette='plasma', s=70)
+axes[2].set_title("Auto Clustering (No Predefined k)")
+
+plt.tight_layout()
+plt.show()