hotiq 1.0.0__tar.gz

hotiq-1.0.0/PKG-INFO

@@ -0,0 +1,6 @@
+Metadata-Version: 2.4
+Name: hotiq
+Version: 1.0.0
+Summary: Simple data preprocessing code helper for Python
+Author: Abhinav B Prasad
+Requires-Python: >=3.9

hotiq-1.0.0/hotiq.egg-info/PKG-INFO

@@ -0,0 +1,6 @@
+Metadata-Version: 2.4
+Name: hotiq
+Version: 1.0.0
+Summary: Simple data preprocessing code helper for Python
+Author: Abhinav B Prasad
+Requires-Python: >=3.9

hotiq-1.0.0/hotiq.egg-info/SOURCES.txt

@@ -0,0 +1,7 @@
+pyproject.toml
+hotiq.egg-info/PKG-INFO
+hotiq.egg-info/SOURCES.txt
+hotiq.egg-info/dependency_links.txt
+hotiq.egg-info/top_level.txt
+preprocessor_helper/__init__.py
+preprocessor_helper/codes.py

hotiq-1.0.0/hotiq.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

hotiq-1.0.0/hotiq.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+dist
+preprocessor_helper

hotiq-1.0.0/preprocessor_helper/__init__.py

@@ -0,0 +1 @@
+from .codes import *

hotiq-1.0.0/preprocessor_helper/codes.py

@@ -0,0 +1,109 @@
+def basic_code():
+    print('''
+import pandas as pd
+import numpy as np
+
+df = pd.read_csv("train.csv")
+
+print(df.head())
+print(df.shape)
+df.info()
+print(df.describe())
+''')
+
+
+def missing_code():
+    print('''
+print(df.isnull().sum())
+
+df["Age"] = df["Age"].fillna(df["Age"].median())
+
+df["Embarked"] = df["Embarked"].fillna(
+    df["Embarked"].mode()[0]
+)
+
+df.drop("Cabin", axis=1, inplace=True)
+''')
+
+
+def duplicate_code():
+    print('''
+print(df.duplicated().sum())
+
+df.drop_duplicates(inplace=True)
+''')
+
+
+def add_column_code():
+    print('''
+# Add a new column with a constant value
+df["New_Column"] = 0
+
+# Titanic example: Family Size
+df["FamilySize"] = df["SibSp"] + df["Parch"] + 1
+
+# Titanic example: Age Group
+df["AgeGroup"] = pd.cut(
+    df["Age"],
+    bins=[0, 18, 40, 60, 100],
+    labels=["Child", "Adult", "Middle Age", "Senior"]
+)
+
+print(df.head())
+''')
+
+
+def drop_column_code():
+    print('''
+df.drop(
+    ["PassengerId", "Name", "Ticket"],
+    axis=1,
+    inplace=True
+)
+''')
+
+
+def encoding_code():
+    print('''
+from sklearn.preprocessing import LabelEncoder
+
+le = LabelEncoder()
+
+df["Sex"] = le.fit_transform(df["Sex"])
+df["Embarked"] = le.fit_transform(df["Embarked"])
+''')
+
+
+def scaling_code():
+    print('''
+from sklearn.preprocessing import MinMaxScaler
+
+scaler = MinMaxScaler()
+
+df[["Age", "Fare"]] = scaler.fit_transform(
+    df[["Age", "Fare"]]
+)
+''')
+
+
+def show_code():
+    print("========== BASIC DATA CHECKING ==========")
+    basic_code()
+
+    print("========== MISSING VALUES ==========")
+    missing_code()
+
+    print("========== DUPLICATE VALUES ==========")
+    duplicate_code()
+
+    print("========== ADDING COLUMNS ==========")
+    add_column_code()
+
+    print("========== DROPPING COLUMNS ==========")
+    drop_column_code()
+
+    print("========== ENCODING ==========")
+    encoding_code()
+
+    print("========== SCALING ==========")
+    scaling_code()

hotiq-1.0.0/pyproject.toml

@@ -0,0 +1,16 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "hotiq"
+version = "1.0.0"
+description = "Simple data preprocessing code helper for Python"
+requires-python = ">=3.9"
+
+authors = [
+    {name = "Abhinav B Prasad"}
+]
+
+[tool.setuptools.packages.find]
+where = ["."]

hotiq-1.0.0/setup.cfg

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