d20-data-preprocess 0.0.1__tar.gz

d20_data_preprocess-0.0.1/.gitignore

@@ -0,0 +1 @@
+src/d20_data_preprocess.egg-info

d20_data_preprocess-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 DEBASHISH TIWARY
+
+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.

d20_data_preprocess-0.0.1/PKG-INFO

@@ -0,0 +1,15 @@
+Metadata-Version: 2.5
+Name: d20-data-preprocess
+Version: 0.0.1
+Summary: A data preprocessing package.
+Project-URL: Homepage, https://github.com/DebashishTiwary/Data_Preprocessor.git
+Author-email: Debashish Tiwary <debasishtewary5@gmail.com>
+License-File: LICENSE
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+
+# Data_Preprocessor
+This project helps in automatic Preprocessing of data during creation of ML models. It is made on top of pandas, numpy, matplotlib.

d20_data_preprocess-0.0.1/README.md

@@ -0,0 +1,2 @@
+# Data_Preprocessor
+This project helps in automatic Preprocessing of data during creation of ML models. It is made on top of pandas, numpy, matplotlib.

d20_data_preprocess-0.0.1/pyproject.toml

@@ -0,0 +1,25 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "d20-data-preprocess"  # This is the name people will use for 'pip install'
+version = "0.0.1"
+authors = [
+  { name="Debashish Tiwary", email="debasishtewary5@gmail.com" },
+]
+description = "A data preprocessing package."
+readme = "README.md"
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/d20_data_preprocess"]
+
+[project.urls]
+Homepage = "https://github.com/DebashishTiwary/Data_Preprocessor.git"

d20_data_preprocess-0.0.1/src/d20_data_preprocess/eda.py

@@ -0,0 +1,136 @@
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+from IPython.display import Image, display
+
+#entering csv file
+def EDA(df,target:any):
+    #check the extension of data
+    #print(df[target])
+    # print("Your Target Column:")
+    # print(df[target])
+    # print('-------------------------------------------------------------------------------------')
+    print("Data Size")
+    print(df.shape)
+    print("Information:")
+    print(df.info())
+    print('-------------------------------------------------------------------------------------')
+    print("Data Description:")
+    print(df.describe())
+    print('-------------------------------------------------------------------------------------')
+    print("Null Values:")
+    print(df.isnull().sum())
+    # print('-------------------------------------------------------------------------------------')
+    plt.figure(figsize=(8,6))
+    plt.title("Heatmap")
+    sns.heatmap(df.corr(numeric_only=True),annot=True,cmap='coolwarm')
+    print('-------------------------------------------------------------------------------------')
+    
+    numerical_features = df.select_dtypes(include=[np.number]).columns.tolist()
+    categorical_features = df.select_dtypes(include=[np.object_]).columns.tolist()
+    print("Numerical Features:{}".format(numerical_features))
+    print("Categorical Features:{}".format(categorical_features))
+    print('-------------------------------------------------------------------------------------')
+    for feature in numerical_features:
+        plt.figure(figsize=(6, 4))
+        plt.title('BoxPlot')
+        sns.histplot(df[feature], kde=True,bins=10)
+        plt.title(f'Distribution of {feature}')
+        plt.xlabel(feature)
+        plt.ylabel('Frequency')
+        plt.show()
+
+    for feature in numerical_features:
+        plt.figure(figsize=(6,4))
+        plt.title('BoxPlot')
+        plt.boxplot(x=df[feature])
+        plt.xlabel(feature)
+        plt.show()
+def showoutliers(df):
+    numerical_features = df.select_dtypes(include=[np.number]).columns.tolist()
+    for feature in numerical_features:
+        plt.figure(figsize=(6,4))
+        plt.title('BoxPlot')
+        plt.boxplot(x=df[feature])
+        plt.xlabel(feature)
+        plt.show()
+def d20help(topic="all"):
+    
+    catalog = {
+        "Data Cleaning & Structuring": {
+            "df.info()": "Prints a summary of the DataFrame, including data types and non-null counts.",
+            "df.describe()": "Generates summary statistics like mean, median, and min/max for numerical columns.",
+            "df.isna().sum()": "Counts the total number of missing (NaN) values in each column.",
+            "df.dropna()": "Removes rows or columns that contain missing or null values.",
+            "df.fillna()": "Replaces missing or null values with a specified value, mean, or median.",
+            "df.drop_duplicates()": "Removes duplicate rows to ensure every record is unique.",
+            "df.astype()": "Casts a column or Series to a specified data type (e.g., float to int).",
+            "df.rename()": "Alters column or row labels using a dictionary mapping.",
+            "df.drop()": "Removes specified rows or columns from the DataFrame."
+        },
+        "Data Transformation & Scaling": {
+            "pd.get_dummies()": "Converts categorical text columns into one-hot encoded numerical variables.",
+            "df.apply()": "Applies a custom function or lambda expression along a DataFrame axis.",
+            "df.map()": "Maps values of a Series using a dictionary or function for label encoding.",
+            "StandardScaler().fit_transform()": "Standardises features by removing the mean and scaling to unit variance.",
+            "MinMaxScaler().fit_transform()": "Rescales numerical features to a specified range, typically 0 to 1.",
+            "KBinsDiscretizer()": "Bins continuous numerical variables into discrete, categorical intervals."
+        },
+        "Reshaping & Combining Data": {
+            "pd.concat()": "Combines multiple DataFrames or Series along a particular axis (rows or columns).",
+            "pd.merge()": "Joins two DataFrames together based on a shared key or index (SQL-style join).",
+            "df.groupby()": "Groups data by specific criteria to allow for aggregate calculations.",
+            "df.pivot()": "Reshapes data from a long format to a wide format based on column values.",
+            "df.melt()": "Unpivots a DataFrame from a wide format to a long format."
+        },
+        "Advanced Feature Engineering": {
+            "train_test_split()": "Splits a dataset into random train and test subsets for model validation.",
+            "SimpleImputer()": "A scikit-learn transformer to handle missing data using mean, median, or mode.",
+            "OneHotEncoder()": "An ML-pipeline friendly scikit-learn transformer for encoding categorical features.",
+            "LabelEncoder()": "Encodes target labels with numerical values between 0 and n-1 classes.",
+            "PCA()": "Reduces dataset dimensionality by projecting data into a lower-dimensional space."
+        }
+    }
+
+    # 2. Logic to handle the "all" argument
+    if topic.lower() == "all":
+        print("=" * 60)
+        print("📊 COMPLETE DATA PREPROCESSING REFERENCE GUIDES 📊")
+        print("=" * 60)
+        
+        for category, functions in catalog.items():
+            print(f"\n🔹 {category}")
+            print("-" * len(category))
+            for func, desc in functions.items():
+                # Formats the print to look clean in the console
+                print(f"  • {func:<32} -> {desc}")
+        print("\n" + "=" * 60)
+
+    elif topic.lower() == 'clean':
+        li=catalog["Data Cleaning & Structuring"]
+        for func, desc in li.items():
+            print(f"-{func:<10} -> {desc}")
+    elif topic.lower() == 'transform':
+        li=catalog["Data Transformation & Scaling"]
+        for key,val in li.items():
+            print(f"-{key:<10} -> {val}")
+    elif topic.lower()=='reshape':
+        li=catalog["Reshaping & Combining Data"]
+        for key,val in li.items():
+            print(f"-{key:<10} -> {val}")
+    elif topic.lower()== 'advance':
+        li=catalog["Advanced Feature Engineering"]
+        for key,val in li.items():
+            print(f"-{key:<10} -> {val}") 
+    else:
+        print(f"Topic '{topic}' not fully mapped yet. Pass 'all' to see all functions.")
+
+
+
+
+
+
+
+
+

d20_data_preprocess-0.0.1/src/d20_data_preprocess/preprocessing.py

@@ -0,0 +1,16 @@
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+from IPython.display import Image, display
+
+def onehotenc(df,value:str):
+    categorical_features = df.select_dtypes(include=[np.object_]).columns.tolist()
+    # if(value!=null):
+    df = pd.get_dummies(df,columns = [value],drop_first=True)
+    return df
+    # else:
+    #     for feature in categorical_features:
+    #         df = pd.get_dummies(df,columns = [feature],drop_first=True)
+def levelenc(df,value:str):
+    df[value]=df[value].map({True:1,False:0})

d20_data_preprocess-0.0.1/tests/dptest.py

@@ -0,0 +1,27 @@
+from IPython.display import display, HTML
+
+def EDA(data):
+    # 1. Perform your Exploratory Data Analysis logic here
+    columns_count = len(data.columns)
+    row_count = len(data)
+    
+    # 2. Design your document-style clickable HTML output
+    html_content = f"""
+    <div style="font-family: 'Arial', sans-serif; line-height: 1.6; max-width: 600px; padding: 15px; border: 1px solid #e0e0e0; border-radius: 5px; background-color: #f9f9f9;">
+        <h3 style="color: #2c3e50; margin-top: 0;">📊 Exploratory Data Analysis Report</h3>
+        <p style="margin: 5px 0;">Your dataset contains <strong>{columns_count} columns</strong> and <strong>{row_count} rows</strong>.</p>
+        
+        <hr style="border: 0; border-top: 1px solid #ccc; margin: 15px 0;">
+        
+        <!-- Clickable actions styled like a document index -->
+        <p style="margin: 8px 0;">
+            👉 <a href="#dataframe_preview" style="color: #1a73e8; text-decoration: none; font-weight: bold;">[View Dataframe Preview]</a>
+        </p>
+        <p style="margin: 8px 0;">
+            👉 <a href="https://pydata.org" target="_blank" style="color: #1a73e8; text-decoration: none; font-weight: bold;">[Open External Pandas Documentation]</a>
+        </p>
+    </div>
+    """
+    # learn here: https://share.google/aimode/7pIaZ8DkgQiwyGqt2
+    # 3. Use display(HTML()) instead of a standard return or print statement
+    display(HTML(html_content))