smilo 0.1.0__tar.gz

smilo-0.1.0/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.4
+Name: smilo
+Version: 0.1.0
+Summary: A beginner-friendly Python data analysis library.
+Author-email: Fahad <dr.fahad1001@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/yourusername/smilo
+Project-URL: Repository, https://github.com/yourusername/smilo
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: matplotlib>=3.7
+Dynamic: license-file
+
+# smilo
+
+A beginner-friendly Python data analysis library for cleaning, splitting, exploring, and visualizing data.
+
+## Installation
+
+pip install smilo
+
+## Usage
+
+from smilo.clean import remove_nulls
+from smilo.split import train_test_split
+from smilo.stats import mean, median, standard_deviation
+from smilo.utils import load_csv, dataset_info
+from smilo.viz import quick_hist
+
+data = [1, None, 2, None, 3]
+clean_data = remove_nulls(data)
+print(clean_data)  # [1, 2, 3]
+
+train, test = train_test_split([1,2,3,4,5,6,7,8,9,10], test_size=0.2, seed=42)
+
+print(mean([1, 2, 3, 4, 5]))  # 3.0
+
+## Modules
+
+- **clean.py** — remove_nulls, fill_nulls, remove_duplicates, remove_empty_strings
+- **split.py** — train_test_split, k_fold_split
+- **stats.py** — mean, median, mode, minimum, maximum, data_range, total, count, variance, standard_deviation
+- **utils.py** — load_csv, dataset_info, column_types
+- **viz.py** — quick_hist, quick_corr
+
+## License
+
+MIT

smilo-0.1.0/README.md

@@ -0,0 +1,35 @@
+# smilo
+
+A beginner-friendly Python data analysis library for cleaning, splitting, exploring, and visualizing data.
+
+## Installation
+
+pip install smilo
+
+## Usage
+
+from smilo.clean import remove_nulls
+from smilo.split import train_test_split
+from smilo.stats import mean, median, standard_deviation
+from smilo.utils import load_csv, dataset_info
+from smilo.viz import quick_hist
+
+data = [1, None, 2, None, 3]
+clean_data = remove_nulls(data)
+print(clean_data)  # [1, 2, 3]
+
+train, test = train_test_split([1,2,3,4,5,6,7,8,9,10], test_size=0.2, seed=42)
+
+print(mean([1, 2, 3, 4, 5]))  # 3.0
+
+## Modules
+
+- **clean.py** — remove_nulls, fill_nulls, remove_duplicates, remove_empty_strings
+- **split.py** — train_test_split, k_fold_split
+- **stats.py** — mean, median, mode, minimum, maximum, data_range, total, count, variance, standard_deviation
+- **utils.py** — load_csv, dataset_info, column_types
+- **viz.py** — quick_hist, quick_corr
+
+## License
+
+MIT

smilo-0.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "smilo"
+version = "0.1.0"
+description = "A beginner-friendly Python data analysis library."
+readme = "README.md"
+requires-python = ">=3.9"
+license = "MIT"
+
+authors = [
+  { name = "Fahad", email = "dr.fahad1001@gmail.com" }
+]
+
+dependencies = [
+  "numpy>=1.24",
+  "pandas>=2.0",
+  "matplotlib>=3.7"
+]
+
+[project.urls]
+Homepage = "https://github.com/yourusername/smilo"
+Repository = "https://github.com/yourusername/smilo"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["smilo*"]

smilo-0.1.0/setup.cfg

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

smilo-0.1.0/smilo/__init__.py

@@ -0,0 +1,7 @@
+from .clean import *
+from .split import *
+from .stats import *
+from .utils import *
+from .viz import *
+
+__version__ = "0.1.0"

smilo-0.1.0/smilo/clean.py

@@ -0,0 +1,31 @@
+"""
+Smilo Data Cleaning Module
+Author: Fahad
+"""
+
+def remove_nulls(data):
+    """
+    Remove None values from a list.
+    """
+    return [item for item in data if item is not None]
+
+
+def fill_nulls(data, value=0):
+    """
+    Replace None values with a specified value.
+    """
+    return [value if item is None else item for item in data]
+
+
+def remove_duplicates(data):
+    """
+    Remove duplicate values while preserving order.
+    """
+    return list(dict.fromkeys(data))
+
+
+def remove_empty_strings(data):
+    """
+    Remove empty strings from a list.
+    """
+    return [item for item in data if item != ""]

smilo-0.1.0/smilo/split.py

@@ -0,0 +1,47 @@
+"""
+Smilo Data Splitting Module
+Author: Fahad
+"""
+
+import random
+
+
+def train_test_split(data, test_size=0.2, seed=None):
+    """
+    Split a list of data into train and test sets.
+
+    Parameters:
+        data (list): The dataset to split.
+        test_size (float): Proportion of data to use as test set (0-1).
+        seed (int): Optional random seed for reproducibility.
+
+    Returns:
+        tuple: (train_data, test_data)
+    """
+    if seed is not None:
+        random.seed(seed)
+
+    shuffled = data.copy()
+    random.shuffle(shuffled)
+
+    split_index = int(len(shuffled) * (1 - test_size))
+    train_data = shuffled[:split_index]
+    test_data = shuffled[split_index:]
+
+    return train_data, test_data
+
+
+def k_fold_split(data, k=5):
+    """
+    Split data into k equal-sized folds for cross-validation.
+
+    Parameters:
+        data (list): The dataset to split.
+        k (int): Number of folds.
+
+    Returns:
+        list of lists: k folds of data.
+    """
+    fold_size = len(data) // k
+    folds = [data[i * fold_size:(i + 1) * fold_size] for i in range(k)]
+    return folds

smilo-0.1.0/smilo/stats.py

@@ -0,0 +1,75 @@
+"""
+Smilo Statistics Module
+Author: Fahad
+"""
+
+from collections import Counter
+
+
+def mean(data):
+    """Return the average of a list."""
+    if not data:
+        raise ValueError("Data cannot be empty.")
+    return sum(data) / len(data)
+
+
+def median(data):
+    """Return the median of a list."""
+    if not data:
+        raise ValueError("Data cannot be empty.")
+
+    data = sorted(data)
+    n = len(data)
+    mid = n // 2
+
+    if n % 2 == 0:
+        return (data[mid - 1] + data[mid]) / 2
+    return data[mid]
+
+
+def mode(data):
+    """Return the most frequent value."""
+    if not data:
+        raise ValueError("Data cannot be empty.")
+
+    count = Counter(data)
+    return count.most_common(1)[0][0]
+
+
+def minimum(data):
+    """Return the minimum value."""
+    return min(data)
+
+
+def maximum(data):
+    """Return the maximum value."""
+    return max(data)
+
+
+def data_range(data):
+    """Return the range (max - min)."""
+    return max(data) - min(data)
+
+
+def total(data):
+    """Return the sum of all values."""
+    return sum(data)
+
+
+def count(data):
+    """Return the number of values."""
+    return len(data)
+
+
+def variance(data):
+    """Return the population variance."""
+    if not data:
+        raise ValueError("Data cannot be empty.")
+
+    avg = mean(data)
+    return sum((x - avg) ** 2 for x in data) / len(data)
+
+
+def standard_deviation(data):
+    """Return the population standard deviation."""
+    return variance(data) ** 0.5

smilo-0.1.0/smilo/utils.py

@@ -0,0 +1,45 @@
+"""
+Smilo Utilities Module
+Author: Fahad
+"""
+
+import pandas as pd
+
+
+def load_csv(filepath):
+    """
+    Load a CSV file into a pandas DataFrame.
+
+    Parameters:
+        filepath (str): Path to the CSV file.
+
+    Returns:
+        pd.DataFrame: Loaded data.
+    """
+    return pd.read_csv(filepath)
+
+
+def dataset_info(df):
+    """
+    Print a quick summary of a DataFrame: shape, columns, missing values.
+
+    Parameters:
+        df (pd.DataFrame): The dataset to inspect.
+    """
+    print(f"Shape: {df.shape}")
+    print(f"Columns: {list(df.columns)}")
+    print("Missing values per column:")
+    print(df.isnull().sum())
+
+
+def column_types(df):
+    """
+    Return a dictionary of column names and their data types.
+
+    Parameters:
+        df (pd.DataFrame): The dataset to inspect.
+
+    Returns:
+        dict: {column_name: dtype}
+    """
+    return df.dtypes.astype(str).to_dict()

smilo-0.1.0/smilo/viz.py

@@ -0,0 +1,43 @@
+"""
+Smilo Visualization Module
+Author: Fahad
+"""
+
+import matplotlib.pyplot as plt
+
+
+def quick_hist(data, column, bins=20, title=None):
+    """
+    Plot a quick histogram for a DataFrame column.
+
+    Parameters:
+        data (pd.DataFrame): The dataset.
+        column (str): Column name to plot.
+        bins (int): Number of histogram bins.
+        title (str): Optional plot title.
+    """
+    plt.figure(figsize=(8, 5))
+    plt.hist(data[column].dropna(), bins=bins, color="skyblue", edgecolor="black")
+    plt.title(title or f"Distribution of {column}")
+    plt.xlabel(column)
+    plt.ylabel("Frequency")
+    plt.show()
+
+
+def quick_corr(data, title="Correlation Heatmap"):
+    """
+    Plot a correlation heatmap for numeric columns in a DataFrame.
+
+    Parameters:
+        data (pd.DataFrame): The dataset.
+        title (str): Plot title.
+    """
+    corr = data.corr(numeric_only=True)
+    plt.figure(figsize=(8, 6))
+    plt.imshow(corr, cmap="coolwarm", interpolation="none")
+    plt.colorbar()
+    plt.xticks(range(len(corr.columns)), corr.columns, rotation=90)
+    plt.yticks(range(len(corr.columns)), corr.columns)
+    plt.title(title)
+    plt.tight_layout()
+    plt.show()

smilo-0.1.0/smilo.egg-info/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.4
+Name: smilo
+Version: 0.1.0
+Summary: A beginner-friendly Python data analysis library.
+Author-email: Fahad <dr.fahad1001@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/yourusername/smilo
+Project-URL: Repository, https://github.com/yourusername/smilo
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: matplotlib>=3.7
+Dynamic: license-file
+
+# smilo
+
+A beginner-friendly Python data analysis library for cleaning, splitting, exploring, and visualizing data.
+
+## Installation
+
+pip install smilo
+
+## Usage
+
+from smilo.clean import remove_nulls
+from smilo.split import train_test_split
+from smilo.stats import mean, median, standard_deviation
+from smilo.utils import load_csv, dataset_info
+from smilo.viz import quick_hist
+
+data = [1, None, 2, None, 3]
+clean_data = remove_nulls(data)
+print(clean_data)  # [1, 2, 3]
+
+train, test = train_test_split([1,2,3,4,5,6,7,8,9,10], test_size=0.2, seed=42)
+
+print(mean([1, 2, 3, 4, 5]))  # 3.0
+
+## Modules
+
+- **clean.py** — remove_nulls, fill_nulls, remove_duplicates, remove_empty_strings
+- **split.py** — train_test_split, k_fold_split
+- **stats.py** — mean, median, mode, minimum, maximum, data_range, total, count, variance, standard_deviation
+- **utils.py** — load_csv, dataset_info, column_types
+- **viz.py** — quick_hist, quick_corr
+
+## License
+
+MIT

smilo-0.1.0/smilo.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+pyproject.toml
+smilo/__init__.py
+smilo/clean.py
+smilo/split.py
+smilo/stats.py
+smilo/utils.py
+smilo/viz.py
+smilo.egg-info/PKG-INFO
+smilo.egg-info/SOURCES.txt
+smilo.egg-info/dependency_links.txt
+smilo.egg-info/requires.txt
+smilo.egg-info/top_level.txt
+tests/test_smilo.py

smilo-0.1.0/smilo.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

smilo-0.1.0/smilo.egg-info/requires.txt

@@ -0,0 +1,3 @@
+numpy>=1.24
+pandas>=2.0
+matplotlib>=3.7

smilo-0.1.0/smilo.egg-info/top_level.txt

@@ -0,0 +1 @@
+smilo

smilo-0.1.0/tests/test_smilo.py

@@ -0,0 +1,85 @@
+"""
+Tests for the smilo library
+Author: Fahad
+"""
+
+import pandas as pd
+
+from smilo.clean import remove_nulls, fill_nulls, remove_duplicates, remove_empty_strings
+from smilo.split import train_test_split, k_fold_split
+from smilo.stats import (
+    mean, median, mode, minimum, maximum,
+    data_range, total, count, variance, standard_deviation
+)
+from smilo.utils import load_csv, dataset_info, column_types
+
+
+# ---------- clean.py ----------
+
+def test_remove_nulls():
+    assert remove_nulls([1, None, 2, None, 3]) == [1, 2, 3]
+
+def test_fill_nulls():
+    assert fill_nulls([1, None, 2], value=0) == [1, 0, 2]
+
+def test_remove_duplicates():
+    assert remove_duplicates([1, 2, 2, 3, 1]) == [1, 2, 3]
+
+def test_remove_empty_strings():
+    assert remove_empty_strings(["a", "", "b", ""]) == ["a", "b"]
+
+
+# ---------- split.py ----------
+
+def test_train_test_split():
+    train, test = train_test_split([1,2,3,4,5,6,7,8,9,10], test_size=0.2, seed=42)
+    assert len(train) == 8
+    assert len(test) == 2
+
+def test_k_fold_split():
+    folds = k_fold_split([1,2,3,4,5,6,7,8,9,10], k=5)
+    assert len(folds) == 5
+    assert all(len(fold) == 2 for fold in folds)
+
+
+# ---------- stats.py ----------
+
+def test_mean():
+    assert mean([1, 2, 3, 4, 5]) == 3.0
+
+def test_median():
+    assert median([1, 2, 3, 4, 5]) == 3
+    assert median([1, 2, 3, 4]) == 2.5
+
+def test_mode():
+    assert mode([1, 2, 2, 3]) == 2
+
+def test_minimum():
+    assert minimum([4, 1, 7, 2]) == 1
+
+def test_maximum():
+    assert maximum([4, 1, 7, 2]) == 7
+
+def test_data_range():
+    assert data_range([4, 1, 7, 2]) == 6
+
+def test_total():
+    assert total([1, 2, 3]) == 6
+
+def test_count():
+    assert count([1, 2, 3, 4]) == 4
+
+def test_variance():
+    assert variance([2, 4, 4, 4, 5, 5, 7, 9]) == 4.0
+
+def test_standard_deviation():
+    assert round(standard_deviation([2, 4, 4, 4, 5, 5, 7, 9]), 2) == 2.0
+
+
+# ---------- utils.py ----------
+
+def test_column_types():
+    df = pd.DataFrame({"a": [1, 2, 3], "b": ["x", "y", "z"]})
+    types = column_types(df)
+    assert types["a"] == "int64"
+    assert types["b"] == "str"