bigdata-helper 0.1.0__py3-none-any.whl

bigdata_helper/__init__.py

@@ -0,0 +1,4 @@
+from .codes import get_code, list_codes  # re-export for simple import surface
+
+__all__ = ["get_code", "list_codes"]
+__version__ = "0.1.0"

bigdata_helper/codes.py

@@ -0,0 +1,170 @@
+
+from typing import Dict, List
+
+def mini_code() -> str:
+    return """
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LinearRegression
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.svm import SVR
+from sklearn.neighbors import KNeighborsRegressor
+from sklearn.metrics import r2_score, mean_squared_error
+
+def load_data(path):
+    data = pd.read_csv(path)
+    X = data[['GRE Score', 'TOEFL Score', 'University Rating', 'SOP', 'LOR', 'CGPA', 'Research']]
+    y = data['Chance of Admit']
+    return X, y
+
+def build_pipeline(model):
+    return Pipeline([
+        ('scaler', StandardScaler()),
+        ('model', model)
+    ])
+
+def evaluate_model(model, X_test, y_test):
+    y_pred = model.predict(X_test)
+    r2 = r2_score(y_test, y_pred)
+    rmse = np.sqrt(mean_squared_error(y_test, y_pred))
+    return r2, rmse
+
+def main():
+    X, y = load_data("Synthetic_Graduate_Admissions.csv")
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    
+    models = {
+        "Linear Regression": LinearRegression(),
+        "Decision Tree": DecisionTreeRegressor(random_state=42),
+        "Random Forest": RandomForestRegressor(random_state=42),
+        "Support Vector Regressor": SVR(kernel='rbf'),
+        "KNN Regressor": KNeighborsRegressor(n_neighbors=5)
+    }
+
+    results = []
+    for name, model in models.items():
+        pipe = build_pipeline(model)
+        pipe.fit(X_train, y_train)
+        r2, rmse = evaluate_model(pipe, X_test, y_test)
+        results.append({"Model": name, "R2 Score": round(r2, 3), "RMSE": round(rmse, 3)})
+
+    results_df = pd.DataFrame(results)
+    print("\\nModel Performance Summary:")
+    print(results_df.to_string(index=False))
+
+    sample = pd.DataFrame([[320, 110, 4, 4.5, 4.0, 9.0, 1]],
+                          columns=['GRE Score', 'TOEFL Score', 'University Rating', 'SOP', 'LOR', 'CGPA', 'Research'])
+    best_model = build_pipeline(RandomForestRegressor(random_state=42))
+    best_model.fit(X, y)
+    pred = best_model.predict(sample)
+    print(f"\\nPredicted Chance of Admission: {pred[0]*100:.2f}%")
+
+if __name__ == "__main__":
+    main()
+"""
+
+def forestfire_code() -> str:
+    return """
+from multiprocessing import Pool
+import pandas as pd
+import sqlite3
+
+
+def mapper(row):
+    return (row["Month"], row["Temperature_Celsius"])
+
+
+def reducer(mapped_data):
+    result = {}
+    for month, temp in mapped_data:
+        result.setdefault(month, []).append(temp)
+    return {m: sum(v) / len(v) for m, v in result.items()}
+
+
+def run_mapreduce(df):
+    with Pool() as p:
+        mapped = p.map(mapper, [row for _, row in df.iterrows()])
+    reduced = reducer(mapped)
+
+    print("\\nAverage Temperature per Month:")
+    for m, t in reduced.items():
+        print(f"{m}: {t:.2f}")
+    return reduced
+
+
+def top_fire_months(df, top_n=5):
+    top = df.groupby("Month")["Burned_Area_hectares"].mean().sort_values(ascending=False).head(top_n)
+    print(f"\\nTop {top_n} Months with Largest Fire Area:\\n{top}\\n")
+    return top
+
+
+def temperature_area_correlation(df):
+    corr = df["Temperature_Celsius"].corr(df["Burned_Area_hectares"])
+    print(f"Correlation between Temperature and Fire Area: {corr:.2f}")
+    return corr
+
+
+def query_avg_area_by_month(conn):
+    query = '''
+        SELECT Month, AVG(Burned_Area_hectares) AS avg_area
+        FROM forestfires
+        GROUP BY Month
+        ORDER BY avg_area DESC;
+    '''
+    result = pd.read_sql_query(query, conn)
+    print("\\nAverage Burned Area by Month (from SQL):")
+    print(result)
+    return result
+
+
+def run_pipeline():
+    print("=== Forest Fire Analysis Pipeline Started ===\\n")
+
+    df = pd.read_csv("forestfires.csv")
+    print(f"Loaded dataset with {len(df)} rows and {len(df.columns)} columns.")
+
+    conn = sqlite3.connect("forestfires.db")
+    df.to_sql("forestfires", conn, if_exists="replace", index=False)
+    print("Data saved to SQLite database.\\n")
+
+    run_mapreduce(df)
+    top_fire_months(df)
+    temperature_area_correlation(df)
+    query_avg_area_by_month(conn)
+
+    print("\\n=== Pipeline Completed Successfully ===")
+
+
+if __name__ == "__main__":
+    run_pipeline()
+"""
+
+def placeholder_code() -> str:
+    return "# Add your next practical code here..."
+
+def get_code_map() -> Dict[str, str]:
+    return {
+        "mini": mini_code(),
+        "forestfire": forestfire_code(),
+        "placeholder": placeholder_code(),
+    }
+
+def get_code(name: str) -> str:
+    """
+    Retrieve a stored code snippet by name.
+    Available names: see list_codes().
+    """
+    key = (name or "").strip().lower()
+    mapping = get_code_map()
+    if key not in mapping:
+        available = ", ".join(sorted(mapping.keys()))
+        raise KeyError(f"Code '{name}' not found. Try one of: {available}")
+    return mapping[key]
+
+def list_codes() -> List[str]:
+    \"Return a list of available code names.\"
+    return sorted(get_code_map().keys())

bigdata_helper-0.1.0.dist-info/METADATA

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: bigdata-helper
+Version: 0.1.0
+Summary: A Python library containing Big Data practical codes for quick access
+Author: Satyam Kale
+License: MIT
+Project-URL: Homepage, https://pypi.org/project/bigdata-helper/
+Keywords: big data,exam,codes,snippets,education
+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
+License-File: LICENSE
+Dynamic: license-file
+
+# bigdata-helper
+
+**Version:** 0.1.0  
+**Author:** Satyam Kale
+
+A lightweight library that stores ready-to-use Big Data practical codes and lets you retrieve them instantly as strings.
+
+> ⚠️ This package is intended for learning, practice, and revision. Use responsibly and follow your institution's academic policies.
+
+## Install
+
+```bash
+pip install bigdata-helper
+```
+
+## Quick Start
+
+```python
+from bigdata_helper import get_code, list_codes
+
+print(list_codes())
+print(get_code("mini"))
+print(get_code("forestfire"))
+```
+
+## Available Codes
+
+- `mini` — Multiple regressors benchmark on a synthetic Graduate Admissions dataset (prints model performance and a sample prediction).
+- `forestfire` — MapReduce-like analysis pipeline for forest fire dataset with SQLite, correlation, and monthly summaries.
+
+## Add More
+
+You can contribute more codes by adding functions to `bigdata_helper/codes.py` and mapping them in `get_code_map()`.

bigdata_helper-0.1.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+bigdata_helper/__init__.py,sha256=lGx6yZpbbcrAzfYykkn98UTlHBm0eKdJtY97JVi3ugo,139
+bigdata_helper/codes.py,sha256=p3iBqSuJDFpTLJUCrlgSK_ZvAWbGYWX0bNWTo28kbE8,5112
+bigdata_helper-0.1.0.dist-info/licenses/LICENSE,sha256=iTPTuqITG-wTuMlwnmMMWhrGaLkb82N_j9bmaTSvRSc,1068
+bigdata_helper-0.1.0.dist-info/METADATA,sha256=_0sX6mHgvrVmcpkUfq-Vl174VytQ21YeLsiwGdJyy7E,1530
+bigdata_helper-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+bigdata_helper-0.1.0.dist-info/top_level.txt,sha256=tVWTBB3_zxa1Y6Rk2rFzjTI-3MrOsymgCaDVBw8n5AQ,15
+bigdata_helper-0.1.0.dist-info/RECORD,,

bigdata_helper-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

bigdata_helper-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Satyam Kale
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

bigdata_helper-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+bigdata_helper