dataquick 0.1.0__tar.gz

dataquick-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 quratalvi11-dotcom
+
+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.

dataquick-0.1.0/PKG-INFO

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: dataquick
+Version: 0.1.0
+Summary: A fast and easy Auto EDA library for data scientists
+Home-page: https://github.com/quratalvi11-dotcom/myproject1
+Author: quratalvi11-dotcom
+License: MIT
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scipy
+Dynamic: author
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# DataQuick 
+
+A fast and easy Auto EDA library for data scientists.
+
+## Features
+- Auto data analysis
+- Missing values report
+- Data cleaning
+- Auto visualizations
+
+## Installation
+```bash
+pip install dataquick
+```
+
+## Usage
+```python
+import pandas as pd
+from dataquick.analyzer import DataAnalyzer
+
+df = pd.read_csv("data.csv")
+analyzer = DataAnalyzer(df)
+analyzer.analyze()
+```

dataquick-0.1.0/README.md

@@ -0,0 +1,24 @@
+# DataQuick 
+
+A fast and easy Auto EDA library for data scientists.
+
+## Features
+- Auto data analysis
+- Missing values report
+- Data cleaning
+- Auto visualizations
+
+## Installation
+```bash
+pip install dataquick
+```
+
+## Usage
+```python
+import pandas as pd
+from dataquick.analyzer import DataAnalyzer
+
+df = pd.read_csv("data.csv")
+analyzer = DataAnalyzer(df)
+analyzer.analyze()
+```

dataquick-0.1.0/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"

dataquick-0.1.0/setup.cfg

@@ -0,0 +1,25 @@
+[metadata]
+name = dataquick
+version = 0.1.0
+author = quratalvi11-dotcom
+description = A fast and easy Auto EDA library for data scientists
+long_description = file: README.md
+long_description_content_type = text/markdown
+url = https://github.com/quratalvi11-dotcom/myproject1
+license = MIT
+
+[options]
+package_dir = = src
+packages = find:
+python_requires = >=3.7
+install_requires = 
+	pandas
+	numpy
+	matplotlib
+	seaborn
+	scipy
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

dataquick-0.1.0/setup.py

@@ -0,0 +1,21 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="dataquick",
+    version="0.1.0",
+    author="quratalvi11-dotcom",
+    description="A fast and easy Auto EDA library for data scientists",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    url="https://github.com/quratalvi11-dotcom/myproject1",
+    package_dir={"": "src"},
+    packages=find_packages(where="src"),
+    python_requires=">=3.7",
+    install_requires=[
+        "pandas",
+        "numpy",
+        "matplotlib",
+        "seaborn",
+        "scipy",
+    ],
+)

dataquick-0.1.0/src/dataquick/__init__.py

@@ -0,0 +1,18 @@
+from .analyzer import DataAnalyzer
+from .cleaner import DataCleaner
+from .visualizer import DataVisualizer
+
+def analyze(df):
+    analyzer = DataAnalyzer(df)
+    analyzer.analyze()
+
+def clean(df, strategy="mean"):
+    cleaner = DataCleaner(df)
+    return cleaner.clean(strategy=strategy)
+
+def visualize(df):
+    visualizer = DataVisualizer(df)
+    visualizer.visualize()
+
+__version__ = "0.1.0"
+__author__ = "quratalvi11-dotcom"

dataquick-0.1.0/src/dataquick/analyzer.py

@@ -0,0 +1,62 @@
+import pandas as pd
+import numpy as np
+
+class DataAnalyzer:
+    def __init__(self, df):
+        if not isinstance(df, pd.DataFrame):
+            raise ValueError("Input must be a pandas DataFrame")
+        self.df = df
+
+    def basic_info(self):
+        print("=" * 50)
+        print("BASIC DATASET INFO")
+        print("=" * 50)
+        print(f"Shape        : {self.df.shape[0]} rows, {self.df.shape[1]} columns")
+        print(f"Total Cells  : {self.df.size}")
+        print(f"\nColumn Names : {list(self.df.columns)}")
+        print(f"\nData Types:")
+        print(self.df.dtypes)
+        print("=" * 50)
+
+    def missing_values(self):
+        print("\n" + "=" * 50)
+        print(" MISSING VALUES REPORT")
+        print("=" * 50)
+        missing = self.df.isnull().sum()
+        percent = (missing / len(self.df)) * 100
+        report = pd.DataFrame({
+            "Missing Count": missing,
+            "Missing %": percent.round(2)
+        })
+        report = report[report["Missing Count"] > 0]
+        if report.empty:
+            print(" No missing values found!")
+        else:
+            print(report)
+        print("=" * 50)
+
+    def duplicates(self):
+        print("\n" + "=" * 50)
+        print(" DUPLICATE ROWS REPORT")
+        print("=" * 50)
+        dup_count = self.df.duplicated().sum()
+        print(f"Duplicate Rows: {dup_count}")
+        if dup_count > 0:
+            print("  Consider removing duplicates!")
+        else:
+            print(" No duplicate rows found!")
+        print("=" * 50)
+
+    def statistics(self):
+        print("\n" + "=" * 50)
+        print("STATISTICAL SUMMARY")
+        print("=" * 50)
+        print(self.df.describe())
+        print("=" * 50)
+
+    def analyze(self):
+        self.basic_info()
+        self.missing_values()
+        self.duplicates()
+        self.statistics()
+        print("\n Analysis Complete!")

dataquick-0.1.0/src/dataquick/cleaner.py

@@ -0,0 +1,61 @@
+import pandas as pd
+import numpy as np
+
+class DataCleaner:
+    def __init__(self, df):
+        if not isinstance(df, pd.DataFrame):
+            raise ValueError("Input must be a pandas DataFrame")
+        self.df = df.copy()
+
+    def remove_duplicates(self):
+        before = len(self.df)
+        self.df = self.df.drop_duplicates()
+        after = len(self.df)
+        print(f"Removed {before - after} duplicate rows")
+        return self
+
+    def fill_missing(self, strategy="mean"):
+        """
+        strategy: 'mean', 'median', 'mode', 'drop'
+        """
+        if strategy == "drop":
+            before = len(self.df)
+            self.df = self.df.dropna()
+            print(f"Dropped {before - len(self.df)} rows with missing values")
+
+        elif strategy == "mean":
+            numeric_cols = self.df.select_dtypes(include=np.number).columns
+            self.df[numeric_cols] = self.df[numeric_cols].fillna(self.df[numeric_cols].mean())
+            print("Filled missing values with mean")
+
+        elif strategy == "median":
+            numeric_cols = self.df.select_dtypes(include=np.number).columns
+            self.df[numeric_cols] = self.df[numeric_cols].fillna(self.df[numeric_cols].median())
+            print("Filled missing values with median")
+
+        elif strategy == "mode":
+            for col in self.df.columns:
+                self.df[col] = self.df[col].fillna(self.df[col].mode()[0])
+            print("Filled missing values with mode")
+
+        return self
+
+    def fix_dtypes(self):
+        for col in self.df.columns:
+            try:
+                self.df[col] = pd.to_numeric(self.df[col])
+            except:
+                pass
+        print("Fixed data types where possible")
+        return self
+
+    def clean(self, strategy="mean"):
+        print("=" * 50)
+        print("AUTO CLEANING STARTED")
+        print("=" * 50)
+        self.remove_duplicates()
+        self.fill_missing(strategy=strategy)
+        self.fix_dtypes()
+        print("=" * 50)
+        print("Cleaning Complete!")
+        return self.df

dataquick-0.1.0/src/dataquick/visualizer.py

@@ -0,0 +1,87 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+class DataVisualizer:
+    def __init__(self, df):
+        if not isinstance(df, pd.DataFrame):
+            raise ValueError("Input must be a pandas DataFrame")
+        self.df = df
+
+    def plot_histograms(self):
+        numeric_cols = self.df.select_dtypes(include=np.number).columns
+        if len(numeric_cols) == 0:
+            print("No numeric columns found for histogram!")
+            return
+        print("Plotting Histograms...")
+        self.df[numeric_cols].hist(
+            figsize=(15, 10),
+            bins=20,
+            color="steelblue",
+            edgecolor="black"
+        )
+        plt.suptitle("Histograms of Numeric Columns", fontsize=16)
+        plt.tight_layout()
+        plt.show()
+
+    def plot_correlation(self):
+        numeric_cols = self.df.select_dtypes(include=np.number)
+        if numeric_cols.empty:
+            print("No numeric columns found for correlation!")
+            return
+        print("Plotting Correlation Heatmap...")
+        plt.figure(figsize=(12, 8))
+        sns.heatmap(
+            numeric_cols.corr(),
+            annot=True,
+            fmt=".2f",
+            cmap="coolwarm",
+            linewidths=0.5
+        )
+        plt.title("Correlation Heatmap", fontsize=16)
+        plt.tight_layout()
+        plt.show()
+
+    def plot_missing(self):
+        missing = self.df.isnull().sum()
+        missing = missing[missing > 0]
+        if missing.empty:
+            print("No missing values to plot!")
+            return
+        print("Plotting Missing Values...")
+        plt.figure(figsize=(10, 6))
+        sns.barplot(x=missing.index, y=missing.values, color="tomato")
+        plt.title("Missing Values Per Column", fontsize=16)
+        plt.xlabel("Columns")
+        plt.ylabel("Missing Count")
+        plt.xticks(rotation=45)
+        plt.tight_layout()
+        plt.show()
+
+    def plot_boxplots(self):
+        numeric_cols = self.df.select_dtypes(include=np.number).columns
+        if len(numeric_cols) == 0:
+            print("No numeric columns found for boxplot!")
+            return
+        print("Plotting Boxplots...")
+        plt.figure(figsize=(15, 8))
+        self.df[numeric_cols].plot(
+            kind="box",
+            figsize=(15, 8),
+            patch_artist=True
+        )
+        plt.title("Boxplots for Outlier Detection", fontsize=16)
+        plt.tight_layout()
+        plt.show()
+
+    def visualize(self):
+        print("=" * 50)
+        print("AUTO VISUALIZATION STARTED")
+        print("=" * 50)
+        self.plot_histograms()
+        self.plot_correlation()
+        self.plot_missing()
+        self.plot_boxplots()
+        print("=" * 50)
+        print("Visualization Complete!")

dataquick-0.1.0/src/dataquick.egg-info/PKG-INFO

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: dataquick
+Version: 0.1.0
+Summary: A fast and easy Auto EDA library for data scientists
+Home-page: https://github.com/quratalvi11-dotcom/myproject1
+Author: quratalvi11-dotcom
+License: MIT
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scipy
+Dynamic: author
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# DataQuick 
+
+A fast and easy Auto EDA library for data scientists.
+
+## Features
+- Auto data analysis
+- Missing values report
+- Data cleaning
+- Auto visualizations
+
+## Installation
+```bash
+pip install dataquick
+```
+
+## Usage
+```python
+import pandas as pd
+from dataquick.analyzer import DataAnalyzer
+
+df = pd.read_csv("data.csv")
+analyzer = DataAnalyzer(df)
+analyzer.analyze()
+```

dataquick-0.1.0/src/dataquick.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+README.md
+pyproject.toml
+setup.cfg
+setup.py
+src/dataquick/__init__.py
+src/dataquick/analyzer.py
+src/dataquick/cleaner.py
+src/dataquick/visualizer.py
+src/dataquick.egg-info/PKG-INFO
+src/dataquick.egg-info/SOURCES.txt
+src/dataquick.egg-info/dependency_links.txt
+src/dataquick.egg-info/requires.txt
+src/dataquick.egg-info/top_level.txt

dataquick-0.1.0/src/dataquick.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dataquick-0.1.0/src/dataquick.egg-info/requires.txt

@@ -0,0 +1,5 @@
+pandas
+numpy
+matplotlib
+seaborn
+scipy

dataquick-0.1.0/src/dataquick.egg-info/top_level.txt

@@ -0,0 +1 @@
+dataquick