UmdTask391_DATA605_Spring2026_YData_profiling

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/.dockerignore

@@ -0,0 +1,143 @@
+# Exclude files from Docker build context. This prevents unnecessary files from
+# being sent to Docker daemon, reducing build time and image size.
+
+# Python artifacts
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+*.egg-info/
+
+# Virtual environments
+venv/
+.venv/
+env/
+.env
+.envrc
+client_venv.helpers/
+ENV/
+
+# Jupyter
+.ipynb_checkpoints/
+.jupyter/
+
+# Build artifacts
+build/
+dist/
+*.eggs/
+.eggs/
+
+# Cache and temporary files
+*.log
+*.tmp
+*.cache
+.pytest_cache/
+.mypy_cache/
+.coverage
+htmlcov/
+
+# Git and version control
+.git/
+.gitignore
+.gitattributes
+.github/
+
+# Docker build scripts (not needed at runtime)
+docker_build.sh
+docker_push.sh
+docker_clean.sh
+docker_exec.sh
+docker_cmd.sh
+docker_bash.sh
+docker_jupyter.sh
+docker_name.sh
+run_jupyter.sh
+Dockerfile.*
+.dockerignore
+
+# Documentation
+README.md
+README.admin.md
+docs/
+*.md
+CHANGELOG.md
+LICENSE
+
+# Configuration and secrets
+.env.*
+.env.local
+.env.development
+.env.production
+.DS_Store
+Thumbs.db
+
+# Shell configuration
+.bashrc
+.bash_history
+.zshrc
+
+# Large data files (mount via volume instead)
+data/
+*.csv
+*.pkl
+*.h5
+*.parquet
+*.feather
+*.arrow
+*.npy
+*.npz
+
+# Generated images
+*.png
+*.jpg
+*.jpeg
+*.gif
+*.svg
+*.pdf
+
+# Test files and examples
+tests/
+test_*
+*_test.py
+tutorials/
+examples/
+
+# IDE and editor files
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.project
+.pydevproject
+.settings/
+*.iml
+.sublime-project
+.sublime-workspace
+
+# Node and frontend (if applicable)
+node_modules/
+npm-debug.log
+yarn-error.log
+.npm
+
+# Requirements management
+requirements.in
+Pipfile
+Pipfile.lock
+poetry.lock
+setup.py
+setup.cfg
+
+# CI/CD configuration
+.gitlab-ci.yml
+.travis.yml
+Jenkinsfile
+.circleci/
+
+# Miscellaneous
+*.bak
+.venv.bak/
+*.whl
+*.tar.gz
+*.zip

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/README.md

@@ -0,0 +1,32 @@
+# YData-profiling Project
+
+## Project Title
+YData Profiling for Exploratory Data Analysis and Regression Modeling
+
+## Project Description
+This project explores the Python library YData-profiling for automated exploratory data analysis (EDA). The goal is to generate comprehensive data profile reports, identify data quality issues, understand variable distributions, and prepare the dataset for predictive modeling.
+
+## Objectives
+- Load and inspect a dataset using Pandas
+- Generate an automated profiling report with YData-profiling
+- Identify missing values, outliers, and data quality issues
+- Perform data cleaning and feature engineering
+- Build a regression model for prediction
+- Evaluate model performance using appropriate metrics
+
+## Tool
+- Python
+- Pandas
+- YData-profiling
+- Scikit-learn
+- Jupyter Notebook
+
+## Dataset
+A public dataset will be selected for profiling and regression analysis.
+
+## Expected Output
+- Automated profiling report
+- Cleaned dataset
+- Regression model
+- Evaluation results
+- Documentation showing how YData-profiling supports the workflow

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/bashrc

@@ -0,0 +1 @@
+set -o vi

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/docker_bash.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+# """
+# This script launches a Docker container with an interactive bash shell for
+# development.
+# """
+
+# Exit immediately if any command exits with a non-zero status.
+set -e
+
+# Print each command to stdout before executing it.
+set -x
+
+# Import the utility functions from the project template.
+GIT_ROOT=$(git rev-parse --show-toplevel)
+source $GIT_ROOT/class_project/project_template/utils.sh
+
+# Load Docker configuration variables for this script.
+get_docker_vars_script ${BASH_SOURCE[0]}
+source $DOCKER_NAME
+print_docker_vars
+
+# List the available Docker images matching the expected image name.
+run "docker image ls $FULL_IMAGE_NAME"
+
+# Configure and run the Docker container with interactive bash shell.
+# - Container is removed automatically on exit (--rm)
+# - Interactive mode with TTY allocation (-ti)
+# - Port forwarding for Jupyter or other services
+# - Current directory mounted to /data inside container
+CONTAINER_NAME=${IMAGE_NAME}_bash
+PORT=8889
+cmd="docker run --rm -ti \
+    --name $CONTAINER_NAME \
+    -p $PORT:$PORT \
+    -v $(pwd):/data \
+    -v $GIT_ROOT:/git_root \
+    -e PYTHONPATH=/git_root:/git_root/helpers_root \
+    $FULL_IMAGE_NAME"
+run $cmd

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/docker_build.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+# """
+# Build a Docker container image for the project.
+#
+# This script sets up the build environment with error handling and command
+# tracing, loads Docker configuration from docker_name.sh, and builds the
+# Docker image using the build_container_image utility function. It supports
+# both single-architecture and multi-architecture builds via the
+# DOCKER_BUILD_MULTI_ARCH environment variable.
+# """
+
+# Exit immediately if any command exits with a non-zero status.
+set -e
+
+# Print each command to stdout before executing it.
+set -x
+
+# Import the utility functions.
+GIT_ROOT=$(git rev-parse --show-toplevel)
+source $GIT_ROOT/class_project/project_template/utils.sh
+
+# Load Docker configuration variables (REPO_NAME, IMAGE_NAME, FULL_IMAGE_NAME).
+get_docker_vars_script ${BASH_SOURCE[0]}
+source $DOCKER_NAME
+print_docker_vars
+
+# Configure Docker build settings.
+# Enable BuildKit for improved build performance and features.
+export DOCKER_BUILDKIT=1
+#export DOCKER_BUILDKIT=0
+
+# Configure single-architecture build (set to 1 for multi-arch build).
+#export DOCKER_BUILD_MULTI_ARCH=1
+export DOCKER_BUILD_MULTI_ARCH=0
+
+# Build the container image.
+# Uncomment the line below to build without using Docker cache.
+#build_container_image --no-cache
+build_container_image

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/docker_clean.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+# """
+# Remove Docker container image for the project.
+#
+# This script cleans up Docker images by removing the container image
+# matching the project configuration. Useful for freeing disk space or
+# ensuring a fresh build.
+# """
+
+# Exit immediately if any command exits with a non-zero status.
+set -e
+
+# Print each command to stdout before executing it.
+set -x
+
+# Import the utility functions.
+GIT_ROOT=$(git rev-parse --show-toplevel)
+source $GIT_ROOT/class_project/project_template/utils.sh
+
+# Load Docker configuration variables for this script.
+get_docker_vars_script ${BASH_SOURCE[0]}
+source $DOCKER_NAME
+print_docker_vars
+
+# Remove the container image.
+remove_container_image

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/docker_cmd.sh

@@ -0,0 +1,42 @@
+#!/bin/bash -e
+# """
+# Execute a command in a Docker container.
+#
+# This script runs a specified command inside a new Docker container instance.
+# The container is removed automatically after the command completes. The
+# current directory is mounted to /data inside the container.
+# """
+
+# Exit immediately if any command exits with a non-zero status.
+set -e
+#set -x
+
+# Capture the command to execute from command-line arguments.
+CMD="$@"
+echo "Executing: '$CMD'"
+
+# Import the utility functions.
+GIT_ROOT=$(git rev-parse --show-toplevel)
+source $GIT_ROOT/class_project/project_template/utils.sh
+
+# Load Docker configuration variables for this script.
+get_docker_vars_script ${BASH_SOURCE[0]}
+source $DOCKER_NAME
+print_docker_vars
+
+# List available Docker images matching the expected image name.
+run "docker image ls $FULL_IMAGE_NAME"
+#(docker manifest inspect $FULL_IMAGE_NAME | grep arch) || true
+
+# Configure and run the Docker container with the specified command.
+DOCKER_RUN_OPTS=""
+CONTAINER_NAME=$IMAGE_NAME
+run "docker run \
+    --rm -ti \
+    --name $CONTAINER_NAME \
+    $DOCKER_RUN_OPTS \
+    -v $(pwd):/data \
+    -v $GIT_ROOT:/git_root \
+    -e PYTHONPATH=/git_root:/git_root/helpers_root \
+    $FULL_IMAGE_NAME \
+    bash -c '$CMD'"

class_project/data605/Spring2026/projects/UmdTask391_DATA605_Spring2026_YData_profiling/docker_exec.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+# """
+# Execute a bash shell in a running Docker container.
+#
+# This script connects to an already running Docker container and opens an
+# interactive bash session for debugging or inspection purposes.
+# """
+
+# Exit immediately if any command exits with a non-zero status.
+set -e
+
+# Print each command to stdout before executing it.
+set -x
+
+# Import the utility functions.
+GIT_ROOT=$(git rev-parse --show-toplevel)
+source $GIT_ROOT/class_project/project_template/utils.sh
+
+# Load Docker configuration variables for this script.
+get_docker_vars_script ${BASH_SOURCE[0]}
+source $DOCKER_NAME
+print_docker_vars
+
+# Execute bash shell in the running container.
+exec_container