scikit-tools 0.1.0__py3-none-any.whl

scikit_tools/__init__.py

@@ -0,0 +1 @@
+from .solutions import *

scikit_tools/solutions.py

@@ -0,0 +1,186 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from scipy import stats
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression, LogisticRegression
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix
+from sklearn.cluster import KMeans
+import os
+
+def ensure_dataset(filepath='iris.csv'):
+    """Ensures that the local dataset exists. If not, automatically downloads and formats it."""
+    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."""
+    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."""
+    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."""
+    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)."""
+    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."""
+    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."""
+    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."""
+    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."""
+    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."""
+    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."""
+    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."""
+    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."""
+    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."""
+    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')
+    }

scikit_tools-0.1.0.dist-info/METADATA

@@ -0,0 +1,19 @@
+Metadata-Version: 2.4
+Name: scikit-tools
+Version: 0.1.0
+Summary: Clean, streamlined Data Science and Machine Learning toolkit with direct topic names
+Author-email: Your Name <your.email@example.com>
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scipy
+Requires-Dist: scikit-learn
+
+# scikit-tools
+A clean, streamlined scientific data science toolkit with self-contained dataset fetching and direct topic interfaces.

scikit_tools-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+scikit_tools/__init__.py,sha256=kVb0Ekjb8KbLLsQj2CGI9FIR2DcnVCcZHCxC052GP6c,25
+scikit_tools/solutions.py,sha256=1Q9_mtTiVg7YsaaVbKQe9BhZnYpfqh24JEhREf20O-o,7644
+scikit_tools-0.1.0.dist-info/METADATA,sha256=IoXPV_gv9tO6Zv1RZM6ItGEfKLFN_18MRsz5kWhMmgQ,684
+scikit_tools-0.1.0.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+scikit_tools-0.1.0.dist-info/top_level.txt,sha256=7oA8qj6fv2Jx-piNasqKzZkzc_2b1aQmdlUoS4XZe-0,13
+scikit_tools-0.1.0.dist-info/RECORD,,

scikit_tools-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

scikit_tools-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+scikit_tools