scikit-tools 0.1.1__tar.gz → 0.1.2__tar.gz

{scikit_tools-0.1.1 → scikit_tools-0.1.2}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: scikit-tools
-Version: 0.1.1
-Summary: Clean, dependency-managed toolkit with fully self-contained topic functions
+Version: 0.1.2
+Summary: Clean, dependency-managed toolkit with raw script segments and dataset handling options
 Author-email: Your Name <your.email@example.com>
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License

{scikit_tools-0.1.1 → scikit_tools-0.1.2}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "scikit-tools"
-version = "0.1.1"
-description = "Clean, dependency-managed toolkit with fully self-contained topic functions"
+version = "0.1.2"
+description = "Clean, dependency-managed toolkit with raw script segments and dataset handling options"
 authors = [
   { name="Your Name", email="your.email@example.com" }
 ]

scikit_tools-0.1.2/src/scikit_tools/solutions.py

@@ -0,0 +1,341 @@
+# scikit-tools solutions library containing raw topic scripts
+
+DATASET_SETUP_CODE = """
+import os
+import pandas as pd
+
+# --- METHOD 1: Direct URL Download & Format (Default) ---
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+print("Fetching dataset from URL...")
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f\"Iris-{x}\")
+df.to_csv('iris.csv', index=False)
+
+# --- METHOD 2: Colab File Upload (Alternative for custom/manual uploads) ---
+# from google.colab import files
+# uploaded = files.upload()
+# df = pd.read_csv('iris.csv')
+
+# --- METHOD 3: Standard Local Check ---
+# if os.path.exists('iris.csv'):
+#     df = pd.read_csv('iris.csv')
+"""
+"""
+This library contains the raw code scripts for all 13 Data Science topics.
+"""
+
+# Topic 1: Basic numerical operations and statistics using NumPy.
+numpy_stats_script = """
+import os
+import pandas as pd
+import numpy as np
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+# Alternatively using Colab uploads:
+# from google.colab import files
+# uploaded = files.upload()
+
+# Load formatted data
+df = pd.read_csv('iris.csv')
+sepal_length = df['SepalLengthCm'].to_numpy()
+
+total_sum = np.sum(sepal_length)
+mean_val = np.mean(sepal_length)
+max_val = np.max(sepal_length)
+min_val = np.min(sepal_length)
+first_five = sepal_length[:5]
+
+print(f"Sum: {total_sum:.2f}")
+print(f"Mean: {mean_val:.2f}")
+print(f"Maximum: {max_val:.2f}")
+print(f"Minimum: {min_val:.2f}")
+print(f"First five values: {first_five}")
+"""
+
+# Topic 2: Load DataFrame and inspect its structure, columns, and shape.
+inspect_dataset_script = """
+import os
+import pandas as pd
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+# Load formatted data
+df = pd.read_csv('iris.csv')
+
+print("--- First 5 Records ---")
+print(df.head())
+print(f"\nNumber of rows: {df.shape[0]}, Number of columns: {df.shape[1]}")
+print("\n--- Column Names & Data Types ---")
+print(df.dtypes)
+print("\n--- Summary Statistics ---")
+print(df.describe())
+"""
+
+# Topic 3: Introduce mock missing values and handle them using median and mode.
+handle_missing_values_script = """
+import os
+import pandas as pd
+import numpy as np
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df_copy = pd.read_csv('iris.csv').copy()
+df_copy.loc[[5, 10, 15], 'SepalLengthCm'] = np.nan
+df_copy.loc[[20, 25], 'Species'] = np.nan
+
+median_sepal = df_copy['SepalLengthCm'].median()
+df_copy['SepalLengthCm'] = df_copy['SepalLengthCm'].fillna(median_sepal)
+mode_species = df_copy['Species'].mode()[0]
+df_copy['Species'] = df_copy['Species'].fillna(mode_species)
+print(df_copy.isnull().sum())
+"""
+
+# Topic 4: Perform one-hot encoding and standardization (scaling).
+data_transformation_script = """
+import os
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+df_encoded = pd.get_dummies(df, columns=['Species'])
+num_cols = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']
+scaler = StandardScaler()
+df_encoded[num_cols] = scaler.fit_transform(df_encoded[num_cols])
+print(df_encoded.head())
+"""
+
+# Topic 5: Generate and render Histogram and Scatter Plots for EDA.
+eda_plots_script = """
+import os
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+fig, axes = plt.subplots(1, 2, figsize=(14, 5))
+sns.histplot(data=df, x='PetalLengthCm', kde=True, color='skyblue', ax=axes[0])
+axes[0].set_title('Histogram of PetalLengthCm')
+sns.scatterplot(data=df, x='SepalLengthCm', y='PetalLengthCm', hue='Species', palette='Set1', ax=axes[1])
+axes[1].set_title('SepalLengthCm vs PetalLengthCm')
+plt.tight_layout()
+plt.show()
+"""
+
+# Topic 6: Quantify outliers using Interquartile Range (IQR) bounds.
+outlier_detection_script = """
+import os
+import pandas as pd
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+Q1 = df['SepalWidthCm'].quantile(0.25)
+Q3 = df['SepalWidthCm'].quantile(0.75)
+IQR = Q3 - Q1
+lower_bound = Q1 - 1.5 * IQR
+upper_bound = Q3 + 1.5 * IQR
+outliers = df[(df['SepalWidthCm'] < lower_bound) | (df['SepalWidthCm'] > upper_bound)]
+print(f"IQR: {IQR:.2f}")
+print(f"Limits: {lower_bound:.2f} to {upper_bound:.2f}")
+print(outliers[['SepalWidthCm', 'Species']])
+"""
+
+# Topic 7: Calculate detailed descriptive metrics.
+descriptive_stats_script = """
+import os
+import pandas as pd
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+attributes = ['SepalLengthCm', 'PetalLengthCm']
+stats_summary = pd.DataFrame({
+    'Mean': df[attributes].mean(),
+    'Median': df[attributes].median(),
+    'Sample Variance': df[attributes].var(),
+    'Standard Deviation': df[attributes].std()
+})
+print(stats_summary)
+"""
+
+# Topic 8: Evaluate covariance and Pearson correlation coefficient.
+correlation_covariance_script = """
+import os
+import pandas as pd
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+covariance_val = df['PetalLengthCm'].cov(df['PetalWidthCm'])
+correlation_val = df['PetalLengthCm'].corr(df['PetalWidthCm'])
+print(f"Covariance: {covariance_val:.4f}")
+print(f"Correlation Coefficient: {correlation_val:.4f}")
+"""
+
+# Topic 9: Run an independent T-test on SepalLengthCm between Setosa and Versicolor.
+hypothesis_testing_script = """
+import os
+import pandas as pd
+from scipy import stats
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+setosa_sepal = df[df['Species'] == 'Iris-setosa']['SepalLengthCm']
+versicolor_sepal = df[df['Species'] == 'Iris-versicolor']['SepalLengthCm']
+t_stat, p_val = stats.ttest_ind(setosa_sepal, versicolor_sepal, equal_var=False)
+print(f"T-statistic: {t_stat:.4f}")
+print(f"P-value: {p_val:.4e}")
+"""
+
+# Topic 10: Linear Regression predicting PetalLengthCm.
+linear_regression_script = """
+import os
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalWidthCm']]
+y = df['PetalLengthCm']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+model = LinearRegression()
+model.fit(X_train, y_train)
+predictions = model.predict(X_test)
+print("Model Coefficients:", model.coef_)
+print("Intercept:", model.intercept_)
+"""
+
+# Topic 11: Multi-class Logistic Regression for classification.
+logistic_regression_script = """
+import os
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score, confusion_matrix
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']]
+y = df['Species']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+clf = LogisticRegression(max_iter=200)
+clf.fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}")
+print(confusion_matrix(y_test, y_pred))
+"""
+
+# Topic 12: Cluster attributes unsupervised using K-Means.
+kmeans_clustering_script = """
+import os
+import pandas as pd
+from sklearn.cluster import KMeans
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']]
+kmeans = KMeans(n_clusters=3, random_state=42, n_init='auto')
+df['Cluster'] = kmeans.fit_predict(X)
+print(df.head())
+"""
+
+# Topic 13: Standardize, compress with 2-Component PCA, and classify.
+pca_analysis_script = """
+import os
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+
+# Dataset Download and Setup
+url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
+df = pd.read_csv(url)
+df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
+df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
+df.to_csv('iris.csv', index=False)
+
+df = pd.read_csv('iris.csv')
+X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']]
+y = df['Species']
+X_scaled = StandardScaler().fit_transform(X)
+pca = PCA(n_components=2)
+X_pca = pca.fit_transform(X_scaled)
+X_train, X_test, y_train, y_test = train_test_split(X_pca, y, test_size=0.2, random_state=42)
+clf = LogisticRegression()
+clf.fit(X_train, y_train)
+y_pred = clf.predict(X_test)
+print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}")
+"""

{scikit_tools-0.1.1 → scikit_tools-0.1.2}/src/scikit_tools.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: scikit-tools
-Version: 0.1.1
-Summary: Clean, dependency-managed toolkit with fully self-contained topic functions
+Version: 0.1.2
+Summary: Clean, dependency-managed toolkit with raw script segments and dataset handling options
 Author-email: Your Name <your.email@example.com>
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License

scikit_tools-0.1.1/src/scikit_tools/solutions.py

@@ -1,205 +0,0 @@
-def ensure_dataset(filepath='iris.csv'):
-    """Ensures that the local dataset exists. If not, automatically downloads and formats it."""
-    import os
-    import pandas as pd
-    if not os.path.exists(filepath):
-        url = 'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv'
-        df = pd.read_csv(url)
-        df.columns = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species']
-        df['Species'] = df['Species'].map(lambda x: f"Iris-{x}")
-        df.to_csv(filepath, index=False)
-
-def numpy_stats(filepath='iris.csv'):
-    """Topic 1: Basic numerical operations and statistics using NumPy."""
-    import pandas as pd
-    import numpy as np
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    sepal_length = df['SepalLengthCm'].to_numpy()
-    return {
-        'sum': np.sum(sepal_length),
-        'mean': np.mean(sepal_length),
-        'max': np.max(sepal_length),
-        'min': np.min(sepal_length),
-        'first_five': sepal_length[:5]
-    }
-
-def inspect_dataset(filepath='iris.csv'):
-    """Topic 2: Load DataFrame and inspect its structure, columns, and shape."""
-    import pandas as pd
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    return {
-        'head': df.head(),
-        'shape': df.shape,
-        'dtypes': df.dtypes,
-        'description': df.describe()
-    }
-
-def handle_missing_values(filepath='iris.csv'):
-    """Topic 3: Introduce mock missing values and handle them using median and mode."""
-    import pandas as pd
-    import numpy as np
-    ensure_dataset(filepath)
-    df_copy = pd.read_csv(filepath).copy()
-    df_copy.loc[[5, 10, 15], 'SepalLengthCm'] = np.nan
-    df_copy.loc[[20, 25], 'Species'] = np.nan
-
-    median_sepal = df_copy['SepalLengthCm'].median()
-    df_copy['SepalLengthCm'] = df_copy['SepalLengthCm'].fillna(median_sepal)
-    mode_species = df_copy['Species'].mode()[0]
-    df_copy['Species'] = df_copy['Species'].fillna(mode_species)
-    return df_copy
-
-def data_transformation(filepath='iris.csv'):
-    """Topic 4: Perform one-hot encoding and standardization (scaling)."""
-    import pandas as pd
-    from sklearn.preprocessing import StandardScaler
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    df_encoded = pd.get_dummies(df, columns=['Species'])
-    num_cols = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']
-    scaler = StandardScaler()
-    df_encoded[num_cols] = scaler.fit_transform(df_encoded[num_cols])
-    return df_encoded
-
-def eda_plots(filepath='iris.csv'):
-    """Topic 5: Generate and render Histogram and Scatter Plots for EDA."""
-    import pandas as pd
-    import matplotlib.pyplot as plt
-    import seaborn as sns
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    fig, axes = plt.subplots(1, 2, figsize=(14, 5))
-    sns.histplot(data=df, x='PetalLengthCm', kde=True, color='skyblue', ax=axes[0])
-    axes[0].set_title('Histogram of PetalLengthCm')
-    sns.scatterplot(data=df, x='SepalLengthCm', y='PetalLengthCm', hue='Species', palette='Set1', ax=axes[1])
-    axes[1].set_title('SepalLengthCm vs PetalLengthCm')
-    plt.tight_layout()
-    plt.show()
-
-def outlier_detection(filepath='iris.csv'):
-    """Topic 6: Quantify outliers using Interquartile Range (IQR) bounds."""
-    import pandas as pd
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    Q1 = df['SepalWidthCm'].quantile(0.25)
-    Q3 = df['SepalWidthCm'].quantile(0.75)
-    IQR = Q3 - Q1
-    lower_bound = Q1 - 1.5 * IQR
-    upper_bound = Q3 + 1.5 * IQR
-    outliers = df[(df['SepalWidthCm'] < lower_bound) | (df['SepalWidthCm'] > upper_bound)]
-    return {
-        'IQR': IQR,
-        'limits': (lower_bound, upper_bound),
-        'outliers': outliers
-    }
-
-def descriptive_stats(filepath='iris.csv'):
-    """Topic 7: Calculate detailed descriptive metrics."""
-    import pandas as pd
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    attributes = ['SepalLengthCm', 'PetalLengthCm']
-    return pd.DataFrame({
-        'Mean': df[attributes].mean(),
-        'Median': df[attributes].median(),
-        'Sample Variance': df[attributes].var(),
-        'Standard Deviation': df[attributes].std()
-    })
-
-def correlation_covariance(filepath='iris.csv'):
-    """Topic 8: Evaluate covariance and Pearson correlation coefficient."""
-    import pandas as pd
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    return {
-        'covariance': df['PetalLengthCm'].cov(df['PetalWidthCm']),
-        'correlation': df['PetalLengthCm'].corr(df['PetalWidthCm'])
-    }
-
-def hypothesis_testing(filepath='iris.csv'):
-    """Topic 9: Run an independent T-test on SepalLengthCm between Setosa and Versicolor."""
-    import pandas as pd
-    from scipy import stats
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    setosa_sepal = df[df['Species'] == 'Iris-setosa']['SepalLengthCm']
-    versicolor_sepal = df[df['Species'] == 'Iris-versicolor']['SepalLengthCm']
-    t_stat, p_val = stats.ttest_ind(setosa_sepal, versicolor_sepal, equal_var=False)
-    return {'t_statistic': t_stat, 'p_value': p_val}
-
-def linear_regression(filepath='iris.csv'):
-    """Topic 10: Linear Regression predicting PetalLengthCm."""
-    import pandas as pd
-    from sklearn.model_selection import train_test_split
-    from sklearn.linear_model import LinearRegression
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalWidthCm']]
-    y = df['PetalLengthCm']
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-    model = LinearRegression()
-    model.fit(X_train, y_train)
-    predictions = model.predict(X_test)
-    return {
-        'coefficients': {col: coef for col, coef in zip(X.columns, model.coef_)},
-        'intercept': model.intercept_,
-        'predictions': pd.DataFrame({'Actual': y_test, 'Predicted': predictions})
-    }
-
-def logistic_regression(filepath='iris.csv'):
-    """Topic 11: Multi-class Logistic Regression for classification."""
-    import pandas as pd
-    from sklearn.model_selection import train_test_split
-    from sklearn.linear_model import LogisticRegression
-    from sklearn.metrics import accuracy_score, confusion_matrix
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']]
-    y = df['Species']
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-    clf = LogisticRegression(max_iter=200)
-    clf.fit(X_train, y_train)
-    y_pred = clf.predict(X_test)
-    return {
-        'accuracy': accuracy_score(y_test, y_pred),
-        'confusion_matrix': confusion_matrix(y_test, y_pred)
-    }
-
-def kmeans_clustering(filepath='iris.csv'):
-    """Topic 12: Cluster attributes unsupervised using K-Means."""
-    import pandas as pd
-    from sklearn.cluster import KMeans
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']]
-    kmeans = KMeans(n_clusters=3, random_state=42, n_init='auto')
-    df['Cluster'] = kmeans.fit_predict(X)
-    return df
-
-def pca_analysis(filepath='iris.csv'):
-    """Topic 13: Standardize, compress with 2-Component PCA, and classify."""
-    import pandas as pd
-    from sklearn.preprocessing import StandardScaler
-    from sklearn.decomposition import PCA
-    from sklearn.model_selection import train_test_split
-    from sklearn.linear_model import LogisticRegression
-    from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
-    ensure_dataset(filepath)
-    df = pd.read_csv(filepath)
-    X = df[['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']]
-    y = df['Species']
-    X_scaled = StandardScaler().fit_transform(X)
-    pca = PCA(n_components=2)
-    X_pca = pca.fit_transform(X_scaled)
-    X_train, X_test, y_train, y_test = train_test_split(X_pca, y, test_size=0.2, random_state=42)
-    clf = LogisticRegression()
-    clf.fit(X_train, y_train)
-    y_pred = clf.predict(X_test)
-    return {
-        'accuracy': accuracy_score(y_test, y_pred),
-        'precision': precision_score(y_test, y_pred, average='macro'),
-        'recall': recall_score(y_test, y_pred, average='macro'),
-        'f1_score': f1_score(y_test, y_pred, average='macro')
-    }