smarteda-shlok 1.0.0__tar.gz

smarteda_shlok-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Shlok Apte
+
+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.

smarteda_shlok-1.0.0/MANIFEST.in

@@ -0,0 +1,3 @@
+include README.md
+include LICENSE
+include requirements.txt

smarteda_shlok-1.0.0/PKG-INFO

@@ -0,0 +1,187 @@
+Metadata-Version: 2.4
+Name: smarteda-shlok
+Version: 1.0.0
+Summary: A lightweight Python library for automated exploratory data analysis (EDA).
+Author: Shlok Apte
+Author-email: Shlok Apte <shlokapte271@gmail.com>
+License: MIT
+Keywords: eda,exploratory-data-analysis,data-analysis,data-science,pandas,numpy,statistics,analytics,machine-learning
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=2.0
+Requires-Dist: numpy>=1.24
+Dynamic: author
+Dynamic: license-file
+Dynamic: requires-python
+
+# SmartEDA
+
+SmartEDA is a lightweight Python library for **Automated Exploratory Data Analysis (EDA)**. It helps data analysts, data scientists, students, and researchers quickly understand their datasets by generating essential statistical insights with a single function call.
+
+---
+
+## ✨ Features
+
+- 📊 Dataset Summary
+- 🧹 Missing Value Analysis
+- 🔁 Duplicate Analysis
+- 📈 Numerical Feature Analysis
+- 📝 Categorical Feature Analysis
+- 🔗 Correlation Analysis
+- 📦 Outlier Detection
+- ⚡ Fast and Lightweight
+- 🐍 One-Line Dataset Analysis
+
+---
+
+## 📦 Installation
+
+```bash
+pip install smarteda
+```
+
+---
+
+## 🚀 Quick Start
+
+```python
+import pandas as pd
+from smarteda import analyzer
+
+# Load dataset
+df = pd.read_csv("Titanic.csv")
+
+# Generate EDA Report
+analyzer(df)
+```
+
+---
+
+## 📋 Example Output
+
+```
+======================================================================
+                        SMARTEDA REPORT
+======================================================================
+
+📊 DATASET SUMMARY
+
+Rows                           : 891
+Columns                        : 12
+Memory Usage (MB)              : 0.28
+Duplicate Rows                 : 0
+Missing Cells                  : 866
+Missing Percentage             : 8.10
+
+🧹 MISSING VALUE ANALYSIS
+
+Total Missing Cells            : 866
+Columns with Missing Values    : 3
+Missing Percentage             : 8.10
+
+🔁 DUPLICATE ANALYSIS
+
+Duplicate Rows                 : 0
+
+📈 NUMERICAL ANALYSIS
+
+...
+
+📝 CATEGORICAL ANALYSIS
+
+...
+
+🔗 CORRELATION ANALYSIS
+
+...
+
+📦 OUTLIER ANALYSIS
+
+...
+```
+
+---
+
+## 📚 Modules
+
+| Module | Description |
+|---------|-------------|
+| `analyzer.py` | Generates the complete EDA report |
+| `summary.py` | Dataset summary |
+| `missing.py` | Missing value analysis |
+| `duplicates.py` | Duplicate row analysis |
+| `numerical.py` | Numerical statistics |
+| `categorical.py` | Categorical feature analysis |
+| `correlation.py` | Correlation analysis |
+| `outliers.py` | Outlier detection |
+
+---
+
+## 💻 Requirements
+
+- Python 3.9 or higher
+- pandas
+- numpy
+
+---
+
+## 📂 Project Structure
+
+```
+smarteda/
+│
+├── src/
+│   └── smarteda/
+│       ├── __init__.py
+│       ├── analyzer.py
+│       ├── summary.py
+│       ├── missing.py
+│       ├── duplicates.py
+│       ├── numerical.py
+│       ├── categorical.py
+│       ├── correlation.py
+│       └── outliers.py
+│
+├── pyproject.toml
+├── README.md
+├── LICENSE
+└── MANIFEST.in
+```
+
+---
+
+## 🎯 Why SmartEDA?
+
+- Beginner-friendly
+- Lightweight and fast
+- Easy to understand
+- Modular architecture
+- Works seamlessly with Pandas DataFrames
+- Designed for quick exploratory data analysis
+
+---
+
+## 📄 License
+
+This project is licensed under the **MIT License**.
+
+---
+
+## 👨‍💻 Author
+
+**Shlok Apte**

smarteda_shlok-1.0.0/README.md

@@ -0,0 +1,156 @@
+# SmartEDA
+
+SmartEDA is a lightweight Python library for **Automated Exploratory Data Analysis (EDA)**. It helps data analysts, data scientists, students, and researchers quickly understand their datasets by generating essential statistical insights with a single function call.
+
+---
+
+## ✨ Features
+
+- 📊 Dataset Summary
+- 🧹 Missing Value Analysis
+- 🔁 Duplicate Analysis
+- 📈 Numerical Feature Analysis
+- 📝 Categorical Feature Analysis
+- 🔗 Correlation Analysis
+- 📦 Outlier Detection
+- ⚡ Fast and Lightweight
+- 🐍 One-Line Dataset Analysis
+
+---
+
+## 📦 Installation
+
+```bash
+pip install smarteda
+```
+
+---
+
+## 🚀 Quick Start
+
+```python
+import pandas as pd
+from smarteda import analyzer
+
+# Load dataset
+df = pd.read_csv("Titanic.csv")
+
+# Generate EDA Report
+analyzer(df)
+```
+
+---
+
+## 📋 Example Output
+
+```
+======================================================================
+                        SMARTEDA REPORT
+======================================================================
+
+📊 DATASET SUMMARY
+
+Rows                           : 891
+Columns                        : 12
+Memory Usage (MB)              : 0.28
+Duplicate Rows                 : 0
+Missing Cells                  : 866
+Missing Percentage             : 8.10
+
+🧹 MISSING VALUE ANALYSIS
+
+Total Missing Cells            : 866
+Columns with Missing Values    : 3
+Missing Percentage             : 8.10
+
+🔁 DUPLICATE ANALYSIS
+
+Duplicate Rows                 : 0
+
+📈 NUMERICAL ANALYSIS
+
+...
+
+📝 CATEGORICAL ANALYSIS
+
+...
+
+🔗 CORRELATION ANALYSIS
+
+...
+
+📦 OUTLIER ANALYSIS
+
+...
+```
+
+---
+
+## 📚 Modules
+
+| Module | Description |
+|---------|-------------|
+| `analyzer.py` | Generates the complete EDA report |
+| `summary.py` | Dataset summary |
+| `missing.py` | Missing value analysis |
+| `duplicates.py` | Duplicate row analysis |
+| `numerical.py` | Numerical statistics |
+| `categorical.py` | Categorical feature analysis |
+| `correlation.py` | Correlation analysis |
+| `outliers.py` | Outlier detection |
+
+---
+
+## 💻 Requirements
+
+- Python 3.9 or higher
+- pandas
+- numpy
+
+---
+
+## 📂 Project Structure
+
+```
+smarteda/
+│
+├── src/
+│   └── smarteda/
+│       ├── __init__.py
+│       ├── analyzer.py
+│       ├── summary.py
+│       ├── missing.py
+│       ├── duplicates.py
+│       ├── numerical.py
+│       ├── categorical.py
+│       ├── correlation.py
+│       └── outliers.py
+│
+├── pyproject.toml
+├── README.md
+├── LICENSE
+└── MANIFEST.in
+```
+
+---
+
+## 🎯 Why SmartEDA?
+
+- Beginner-friendly
+- Lightweight and fast
+- Easy to understand
+- Modular architecture
+- Works seamlessly with Pandas DataFrames
+- Designed for quick exploratory data analysis
+
+---
+
+## 📄 License
+
+This project is licensed under the **MIT License**.
+
+---
+
+## 👨‍💻 Author
+
+**Shlok Apte**

smarteda_shlok-1.0.0/pyproject.toml

@@ -0,0 +1,57 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "smarteda-shlok"
+version = "1.0.0"
+description = "A lightweight Python library for automated exploratory data analysis (EDA)."
+
+readme = "README.md"
+requires-python = ">=3.9"
+
+authors = [
+    { name = "Shlok Apte", email = "shlokapte271@gmail.com" }
+]
+
+license = { text = "MIT" }
+
+keywords = [
+    "eda",
+    "exploratory-data-analysis",
+    "data-analysis",
+    "data-science",
+    "pandas",
+    "numpy",
+    "statistics",
+    "analytics",
+    "machine-learning"
+]
+
+dependencies = [
+    "pandas>=2.0",
+    "numpy>=1.24"
+]
+
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Software Development :: Libraries",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13"
+]
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]

smarteda_shlok-1.0.0/requirements.txt

@@ -0,0 +1,6 @@
+pandas
+numpy
+matplotlib
+seaborn
+openpyxl
+ipython

smarteda_shlok-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

smarteda_shlok-1.0.0/setup.py

@@ -0,0 +1,41 @@
+from setuptools import setup, find_packages
+
+
+setup(
+    name="smarteda-shlok",
+    version="1.0.0",
+
+    author="Shlok Apte",
+    author_email="shlokapte271@gmail.com",
+
+    description="Automated Exploratory Data Analysis Python Library",
+
+    long_description=open(
+        "README.md",
+        encoding="utf-8"
+    ).read(),
+
+    long_description_content_type="text/markdown",
+
+    packages=find_packages(),
+
+    install_requires=[
+        "pandas",
+        "numpy",
+        "matplotlib",
+        "seaborn",
+        "openpyxl",
+        "ipython"
+    ],
+
+    python_requires=">=3.8",
+
+    license="MIT",
+
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+        "Topic :: Scientific/Engineering :: Information Analysis"
+    ],
+)

smarteda_shlok-1.0.0/src/smarteda/__init__.py

@@ -0,0 +1,3 @@
+from .analyzer import analyzer
+
+__version__ = "1.0.0"

smarteda_shlok-1.0.0/src/smarteda/analyzer.py

@@ -0,0 +1,121 @@
+import pandas as pd
+from IPython.display import display
+
+from .summary import dataset_summary
+from .missing import missing_summary
+from .duplicates import duplicate_analysis
+from .numerical import numerical_analysis
+from .categorical import categorical_analysis
+from .correlation import correlation_analysis
+from .outliers import outlier_analysis
+
+
+def analyzer(df, return_report=False):
+
+    summary = dataset_summary(df)
+    missing = missing_summary(df)
+    duplicates = duplicate_analysis(df)
+    numerical = numerical_analysis(df)
+    categorical= categorical_analysis(df)
+    correlation= correlation_analysis(df)
+    outliers= outlier_analysis(df)
+
+
+
+
+    print("="*70)
+    print("SMARTEDA REPORT")
+    print("="*70)
+
+
+    # Dataset Summary
+    print("\n📊 DATASET SUMMARY")
+
+    display(
+        pd.DataFrame(
+            summary.items(),
+            columns=["Metric", "Value"]
+        ).style.hide(axis="index")
+    )
+
+
+    # Missing Value Analysis
+    print("\n🧹 MISSING VALUE ANALYSIS")
+
+    display(
+        pd.DataFrame(
+            missing.items(),
+            columns=["Metric", "Value"]
+        ).style.hide(axis="index")
+    )
+
+
+    # Duplicate Analysis
+    print("\n🔁 DUPLICATE VALUE ANALYSIS")
+
+    duplicate_report = {
+        "Total Rows": duplicates["Total Rows"],
+        "Duplicate Rows": duplicates["Duplicate Rows"],
+        "Duplicate Percentage": duplicates["Duplicate Percentage"]
+    }
+
+
+    display(
+        pd.DataFrame(
+            duplicate_report.items(),
+            columns=["Metric", "Value"]
+        ).style.hide(axis="index")
+    )
+
+
+    print("\n🔢 NUMERICAL ANALYSIS")
+    display(
+        numerical
+    )
+
+    print("\n🔤 CATEGORICAL ANALYSIS")
+
+    display(categorical)
+
+
+    print("\n🔗 CORRELATION ANALYSIS")
+
+
+    print("\nCorrelation Matrix")
+
+    display(
+        correlation["Correlation Matrix"]
+    )
+
+
+    print("\nStrong Correlations")
+
+    if not correlation["Strong Correlations"].empty:
+
+        display(
+            correlation["Strong Correlations"]
+        )
+
+    else:
+
+        print("No highly correlated features found")
+        
+
+    print("\n🚨 OUTLIER ANALYSIS")
+
+    display(outliers)
+
+
+
+
+    if return_report:
+        return {
+            "summary": summary,
+            "missing": missing,
+            "duplicates": duplicates,
+            "numerical": numerical,
+            "categorical": categorical,
+            "correlation": correlation,
+            "outliers": outliers,
+           
+        }

smarteda_shlok-1.0.0/src/smarteda/categorical.py

@@ -0,0 +1,46 @@
+import pandas as pd
+
+
+def categorical_analysis(df):
+
+    try:
+
+        # Select categorical columns
+        cat_df = df.select_dtypes(
+            include="object"
+        )
+
+
+        result = pd.DataFrame({
+
+            "Column": cat_df.columns,
+
+            "Count": cat_df.count(),
+
+            "Unique": cat_df.nunique(),
+
+            "Top": [
+                cat_df[col].mode()[0]
+                if not cat_df[col].mode().empty
+                else None
+                for col in cat_df.columns
+            ],
+
+            "Frequency": [
+                cat_df[col].value_counts().iloc[0]
+                if not cat_df[col].value_counts().empty
+                else 0
+                for col in cat_df.columns
+            ]
+
+        })
+
+
+        return result.reset_index(drop=True)
+
+
+    except Exception as e:
+
+        return pd.DataFrame(
+            {"Error":[str(e)]}
+        )

smarteda_shlok-1.0.0/src/smarteda/correlation.py

@@ -0,0 +1,56 @@
+import pandas as pd
+
+
+def correlation_analysis(df):
+
+    try:
+
+        # Select numerical columns only
+        num_df = df.select_dtypes(
+            include="number"
+        )
+
+
+        # Correlation matrix
+        correlation = num_df.corr()
+
+
+        # Find strong correlations
+        corr_pairs = []
+
+        for col1 in correlation.columns:
+            for col2 in correlation.columns:
+
+                if col1 < col2:
+
+                    value = correlation.loc[
+                        col1, col2
+                    ]
+
+                    if abs(value) >= 0.7:
+
+                        corr_pairs.append(
+                            {
+                                "Feature 1": col1,
+                                "Feature 2": col2,
+                                "Correlation": round(value, 2)
+                            }
+                        )
+
+
+        strong_corr = pd.DataFrame(
+            corr_pairs
+        )
+
+
+        return {
+            "Correlation Matrix": correlation,
+            "Strong Correlations": strong_corr
+        }
+
+
+    except Exception as e:
+
+        return {
+            "Error": str(e)
+        }

smarteda_shlok-1.0.0/src/smarteda/duplicates.py

@@ -0,0 +1,45 @@
+import pandas as pd
+
+
+def duplicate_analysis(df):
+    """
+    Function to analyze duplicate records
+    """
+
+    result = {}
+
+    try:
+        # Total rows
+        total_rows = df.shape[0]
+
+        # Duplicate rows count
+        duplicate_count = df.duplicated().sum()
+
+        # Duplicate percentage
+        duplicate_percentage = (duplicate_count / total_rows) * 100
+
+
+        result["Total Rows"] = total_rows
+        result["Duplicate Rows"] = duplicate_count
+        result["Duplicate Percentage"] = round(
+            duplicate_percentage, 2
+        )
+
+
+        # Duplicate dataframe
+        duplicate_data = df[df.duplicated(keep=False)]
+
+        result["Duplicate Data"] = duplicate_data
+
+
+        # Remove duplicates
+        cleaned_df = df.drop_duplicates()
+
+        result["Cleaned Data"] = cleaned_df
+
+
+    except Exception as e:
+        result["Error"] = str(e)
+
+
+    return result

smarteda_shlok-1.0.0/src/smarteda/missing.py

@@ -0,0 +1,45 @@
+import pandas as pd
+
+
+def missing_summary(df):
+
+    try:
+
+        # Missing count per column
+        missing_count = df.isnull().sum()
+
+
+        # Keep only columns having missing values
+        missing_columns = missing_count[
+            missing_count > 0
+        ]
+
+
+        result = {
+
+            "Total Missing Cells": int(
+                missing_count.sum()
+            ),
+
+            "Missing Percentage": round(
+                (missing_count.sum() / df.size) * 100,
+                2
+            ),
+
+            "Columns With Missing Values": list(
+                missing_columns.index
+            ),
+
+            "Missing Count By Column": missing_columns.to_dict()
+
+        }
+
+
+        return result
+
+
+    except Exception as e:
+
+        return {
+            "Error": str(e)
+        }

smarteda_shlok-1.0.0/src/smarteda/numerical.py

@@ -0,0 +1,20 @@
+import pandas as pd
+
+
+def numerical_analysis(df):
+
+    try:
+        # Select numerical columns
+        num_df = df.select_dtypes(include="number")
+
+        # Apply describe on all numerical columns
+        result = num_df.describe().T
+
+        # Add extra useful information
+        result["missing"] = num_df.isnull().sum()
+        result["unique"] = num_df.nunique()
+
+        return result
+
+    except Exception as e:
+        return {"Error": str(e)}

smarteda_shlok-1.0.0/src/smarteda/outliers.py

@@ -0,0 +1,62 @@
+import pandas as pd
+
+
+def outlier_analysis(df):
+
+    try:
+
+        # Select numerical columns
+        num_df = df.select_dtypes(
+            include="number"
+        )
+
+
+        result = []
+
+
+        for col in num_df.columns:
+
+            Q1 = num_df[col].quantile(0.25)
+
+            Q3 = num_df[col].quantile(0.75)
+
+            IQR = Q3 - Q1
+
+
+            lower = Q1 - 1.5 * IQR
+
+            upper = Q3 + 1.5 * IQR
+
+
+            outliers = num_df[
+                (num_df[col] < lower) |
+                (num_df[col] > upper)
+            ][col].count()
+
+
+            percentage = (
+                outliers / len(df)
+            ) * 100
+
+
+            result.append({
+
+                "Column": col,
+
+                "Outliers": outliers,
+
+                "Outlier Percentage": round(
+                    percentage, 2
+                )
+
+            })
+
+
+        return pd.DataFrame(result)
+
+
+    except Exception as e:
+
+        return pd.DataFrame(
+            {"Error":[str(e)]}
+        )

smarteda_shlok-1.0.0/src/smarteda/summary.py

@@ -0,0 +1,56 @@
+import pandas as pd
+
+
+def dataset_summary(df: pd.DataFrame) -> dict:
+    """
+    Generate a summary of a pandas DataFrame.
+
+    Parameters
+    ----------
+    df : pandas.DataFrame
+        Input DataFrame.
+
+    Returns 
+    -------
+    dict
+        Dataset summary statistics.
+    """
+
+    if not isinstance(df, pd.DataFrame):
+        raise TypeError("Input must be a pandas DataFrame.")
+
+    rows = df.shape[0]
+    columns = df.shape[1]
+
+    memory = round(df.memory_usage(deep=True).sum() / (1024 ** 2), 2)
+
+    duplicate_rows = int(df.duplicated().sum())
+
+    missing_cells = int(df.isnull().sum().sum())
+
+    missing_percentage = round(
+        (missing_cells / (rows * columns)) * 100, 2
+    ) if rows and columns else 0
+
+    numeric_columns = len(df.select_dtypes(include="number").columns)
+
+    categorical_columns = len(
+        df.select_dtypes(include=["object", "category"]).columns
+    )
+
+    boolean_columns = len(df.select_dtypes(include="bool").columns)
+
+    datetime_columns = len(df.select_dtypes(include="datetime").columns)
+
+    return {
+        "Rows": rows,
+        "Columns": columns,
+        "Memory Usage (MB)": memory,
+        "Duplicate Rows": duplicate_rows,
+        "Missing Cells": missing_cells,
+        "Missing Percentage": missing_percentage,
+        "Numeric Columns": numeric_columns,
+        "Categorical Columns": categorical_columns,
+        "Boolean Columns": boolean_columns,
+        "Datetime Columns": datetime_columns,
+    }

smarteda_shlok-1.0.0/src/smarteda_shlok.egg-info/PKG-INFO

@@ -0,0 +1,187 @@
+Metadata-Version: 2.4
+Name: smarteda-shlok
+Version: 1.0.0
+Summary: A lightweight Python library for automated exploratory data analysis (EDA).
+Author: Shlok Apte
+Author-email: Shlok Apte <shlokapte271@gmail.com>
+License: MIT
+Keywords: eda,exploratory-data-analysis,data-analysis,data-science,pandas,numpy,statistics,analytics,machine-learning
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=2.0
+Requires-Dist: numpy>=1.24
+Dynamic: author
+Dynamic: license-file
+Dynamic: requires-python
+
+# SmartEDA
+
+SmartEDA is a lightweight Python library for **Automated Exploratory Data Analysis (EDA)**. It helps data analysts, data scientists, students, and researchers quickly understand their datasets by generating essential statistical insights with a single function call.
+
+---
+
+## ✨ Features
+
+- 📊 Dataset Summary
+- 🧹 Missing Value Analysis
+- 🔁 Duplicate Analysis
+- 📈 Numerical Feature Analysis
+- 📝 Categorical Feature Analysis
+- 🔗 Correlation Analysis
+- 📦 Outlier Detection
+- ⚡ Fast and Lightweight
+- 🐍 One-Line Dataset Analysis
+
+---
+
+## 📦 Installation
+
+```bash
+pip install smarteda
+```
+
+---
+
+## 🚀 Quick Start
+
+```python
+import pandas as pd
+from smarteda import analyzer
+
+# Load dataset
+df = pd.read_csv("Titanic.csv")
+
+# Generate EDA Report
+analyzer(df)
+```
+
+---
+
+## 📋 Example Output
+
+```
+======================================================================
+                        SMARTEDA REPORT
+======================================================================
+
+📊 DATASET SUMMARY
+
+Rows                           : 891
+Columns                        : 12
+Memory Usage (MB)              : 0.28
+Duplicate Rows                 : 0
+Missing Cells                  : 866
+Missing Percentage             : 8.10
+
+🧹 MISSING VALUE ANALYSIS
+
+Total Missing Cells            : 866
+Columns with Missing Values    : 3
+Missing Percentage             : 8.10
+
+🔁 DUPLICATE ANALYSIS
+
+Duplicate Rows                 : 0
+
+📈 NUMERICAL ANALYSIS
+
+...
+
+📝 CATEGORICAL ANALYSIS
+
+...
+
+🔗 CORRELATION ANALYSIS
+
+...
+
+📦 OUTLIER ANALYSIS
+
+...
+```
+
+---
+
+## 📚 Modules
+
+| Module | Description |
+|---------|-------------|
+| `analyzer.py` | Generates the complete EDA report |
+| `summary.py` | Dataset summary |
+| `missing.py` | Missing value analysis |
+| `duplicates.py` | Duplicate row analysis |
+| `numerical.py` | Numerical statistics |
+| `categorical.py` | Categorical feature analysis |
+| `correlation.py` | Correlation analysis |
+| `outliers.py` | Outlier detection |
+
+---
+
+## 💻 Requirements
+
+- Python 3.9 or higher
+- pandas
+- numpy
+
+---
+
+## 📂 Project Structure
+
+```
+smarteda/
+│
+├── src/
+│   └── smarteda/
+│       ├── __init__.py
+│       ├── analyzer.py
+│       ├── summary.py
+│       ├── missing.py
+│       ├── duplicates.py
+│       ├── numerical.py
+│       ├── categorical.py
+│       ├── correlation.py
+│       └── outliers.py
+│
+├── pyproject.toml
+├── README.md
+├── LICENSE
+└── MANIFEST.in
+```
+
+---
+
+## 🎯 Why SmartEDA?
+
+- Beginner-friendly
+- Lightweight and fast
+- Easy to understand
+- Modular architecture
+- Works seamlessly with Pandas DataFrames
+- Designed for quick exploratory data analysis
+
+---
+
+## 📄 License
+
+This project is licensed under the **MIT License**.
+
+---
+
+## 👨‍💻 Author
+
+**Shlok Apte**

smarteda_shlok-1.0.0/src/smarteda_shlok.egg-info/SOURCES.txt

@@ -0,0 +1,20 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+requirements.txt
+setup.py
+src/smarteda/__init__.py
+src/smarteda/analyzer.py
+src/smarteda/categorical.py
+src/smarteda/correlation.py
+src/smarteda/duplicates.py
+src/smarteda/missing.py
+src/smarteda/numerical.py
+src/smarteda/outliers.py
+src/smarteda/summary.py
+src/smarteda_shlok.egg-info/PKG-INFO
+src/smarteda_shlok.egg-info/SOURCES.txt
+src/smarteda_shlok.egg-info/dependency_links.txt
+src/smarteda_shlok.egg-info/requires.txt
+src/smarteda_shlok.egg-info/top_level.txt

smarteda_shlok-1.0.0/src/smarteda_shlok.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

smarteda_shlok-1.0.0/src/smarteda_shlok.egg-info/requires.txt

@@ -0,0 +1,2 @@
+pandas>=2.0
+numpy>=1.24

smarteda_shlok-1.0.0/src/smarteda_shlok.egg-info/top_level.txt

@@ -0,0 +1 @@
+smarteda