rpstats 1.0.0__tar.gz

rpstats-1.0.0/LICENSE

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

rpstats-1.0.0/PKG-INFO

@@ -0,0 +1,224 @@
+Metadata-Version: 2.4
+Name: rpstats
+Version: 1.0.0
+Summary: Clinical Data Programming and Statistical Analysis Practical Code Library.
+License-Expression: MIT
+Keywords: clinical-trials,biostatistics,clinical-data-programming,cdisc,sdtm,adam,pharmaceutical,r-programming,data-science,statistics
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: R
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Dynamic: license-file
+
+# rpstats
+
+[![PyPI Version](https://img.shields.io/badge/pypi-v1.0.0-blue.svg)](https://pypi.org/project/rpstats/)
+[![Python Versions](https://img.shields.io/badge/python-3.8%20|%203.9%20|%203.10%20|%203.11%20|%203.12%20|%203.13-blue.svg)](https://pypi.org/project/rpstats/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+
+**rpstats** (*Reproducible Practical Statistics*) is a lightweight, professional Python package designed for biostatistics students, clinical data programmers, and researchers preparing for practical examinations and laboratory coursework.
+
+It contains **8 complete clinical data programming and statistical analysis practical experiments**, providing complete, clean, practical-ready code in **both Python and R**.
+
+---
+
+## Key Features
+
+- **Dual-Language Practical Code**: Instant access to complete, tested implementations in Python and R for every experiment.
+- **Zero Heavy Dependencies**: Installs instantly without requiring pandas, NumPy, SciPy, or R. Runs on any computer, standard college laboratory workstation, or laptop.
+- **Exam & Laboratory Ready**: Formatted for quick copy-pasting directly into Jupyter Notebook, Google Colab, or RStudio.
+- **Statistically & Clinically Sound**: Follows industry standards including CDISC SDTM / ADaM dataset architecture, standard clinical blood pressure guidelines, and statistical testing methodologies.
+
+---
+
+## Installation
+
+### Standard Installation (via PyPI)
+
+```bash
+pip install rpstats
+```
+
+### Local Development Installation
+
+Install in editable mode from the project directory:
+
+```bash
+pip install -e .
+```
+
+---
+
+## Quick Start & Usage
+
+Import the package in Python or inside a Jupyter Notebook:
+
+```python
+import rpstats
+
+# 1. Display package version
+rpstats.version()
+
+# 2. View the catalog of all 8 experiments
+rpstats.help()
+
+# 3. Print complete Python & R programs for any experiment
+rpstats.exp1()  # Data Import and Exploration
+rpstats.exp2()  # Data Cleaning
+rpstats.exp3()  # Data Transformation
+rpstats.exp4()  # Data Visualization
+rpstats.exp5()  # SDTM Dataset Creation
+rpstats.exp6()  # ADaM Dataset Creation
+rpstats.exp7()  # Statistical Analysis
+rpstats.exp8()  # Clinical Tables and Figures
+```
+
+---
+
+## Experiments Catalog
+
+| Function | Experiment Title | Input Files | Primary Output Files |
+| :--- | :--- | :--- | :--- |
+| `rpstats.exp1()` | **Data Import and Exploration** | `clinical_data.csv` | Terminal inspection output |
+| `rpstats.exp2()` | **Data Cleaning** | `clinical_trial_data_raw.csv` | `clinical_trial_data_cleaned.csv` |
+| `rpstats.exp3()` | **Data Transformation** | `clinical_demographics.csv`, `clinical_vitals_labs.csv` | `clinical_trial_data_analysis.csv` |
+| `rpstats.exp4()` | **Data Visualization** | `clinical_visualization_data.csv` | 5 High-res PNG plots (`dpi=300`) |
+| `rpstats.exp5()` | **SDTM Dataset Creation** | 5 Raw clinical domains | `dm_sdtm.csv`, `vs_sdtm.csv`, `lb_sdtm.csv`, `ae_sdtm.csv`, `ex_sdtm.csv` |
+| `rpstats.exp6()` | **ADaM Dataset Creation** | 5 SDTM domains | `adsl.csv`, `advs.csv`, `adlb.csv`, `adae.csv` |
+| `rpstats.exp7()` | **Statistical Analysis** | `adam_exp7_analysis.csv` | `placebo_sbp_qqplot.png`, `statistical_analysis_results.csv` |
+| `rpstats.exp8()` | **Clinical Tables and Figures** | `adsl_exp8.csv`, `advs_exp8.csv`, `adae_exp8.csv` | Tables 14.1.1, 14.2.1, 14.3.1 (CSV), Figures 14.2.1, 14.2.2 (PNG) |
+
+---
+
+## Experiment Details
+
+### Experiment 1: Data Import and Exploration
+- **Objective**: Import and inspect clinical trial datasets.
+- **Python**: Uses `pandas` and `numpy` to display the first and last records, shape, column names, data types, summary statistics, and missing value counts.
+- **R**: Uses base R to inspect dimensions, structure (`str()`), column names, summary statistics, missing values per column, and complete case counts.
+
+### Experiment 2: Data Cleaning
+- **Objective**: Perform essential clinical data cleaning tasks.
+- **Key Operations**:
+  - Impute numeric missing values using column medians.
+  - Impute missing site identifiers (`SITEID`) with `"Unknown"`.
+  - Identify and remove exact duplicate rows.
+  - Deduplicate patient records (`USUBJID`), retaining the first record.
+  - Standardize patient sex into `'M'` and `'F'`.
+  - Save cleaned data to `clinical_trial_data_cleaned.csv`.
+
+### Experiment 3: Data Transformation
+- **Objective**: Merge demographics with clinical vitals/labs and derive key study indicators.
+- **Key Operations**:
+  - Verify subject identifier (`USUBJID`) uniqueness and merge datasets using an inner join.
+  - Derive age groups (`<65`, `>=65`).
+  - Derive clinical blood pressure categories (`Normal`, `Elevated`, `Stage 1 Hypertension`, `Stage 2 Hypertension`).
+  - Calculate days on study (`DAYS_ON_STUDY`) against a configurable cutoff date.
+  - Derive clinical high-risk flag (`HIGH_RISK_FLAG`).
+  - Save merged dataset as `clinical_trial_data_analysis.csv`.
+
+### Experiment 4: Clinical Data Visualization
+- **Objective**: Generate publication-grade, high-resolution figures.
+- **Figures Generated**:
+  1. `age_histogram.png`: Age distribution with kernel density curve.
+  2. `sex_barchart.png`: Subject count by sex.
+  3. `bmi_by_agegroup_boxplot.png`: BMI distribution grouped by age category.
+  4. `glucose_by_arm_histogram.png`: Fasting glucose distribution across treatment arms.
+  5. `height_weight_scatterplot.png`: Height vs. weight scatter plot categorized by sex.
+
+### Experiment 5: SDTM Dataset Creation
+- **Objective**: Transform raw source data into standardized CDISC SDTM domain structures.
+- **Domains Produced**:
+  - `DM` (Demographics): Subject identifiers, age, sex, race, treatment arm, date ISO standardizations.
+  - `VS` (Vital Signs): Wide-to-long transformation of SYSBP, DIABP, PULSE, and TEMP with sequence numbering (`VSSEQ`).
+  - `LB` (Laboratory): Wide-to-long transformation of GLUC, ALT, AST, and BILI with sequence numbering (`LBSEQ`).
+  - `AE` (Adverse Events): Standardized severity (`MILD`, `MODERATE`, `SEVERE`), start/end dates, sequence numbering (`AESEQ`).
+  - `EX` (Exposure): Standardized treatment dosing records and sequence numbering (`EXSEQ`).
+
+### Experiment 6: ADaM Dataset Creation
+- **Objective**: Build CDISC ADaM datasets for statistical analysis.
+- **Datasets Produced**:
+  - `ADSL` (Subject-Level Analysis Dataset): Incorporates exposure metrics, treatment start/end dates, safety population flag (`SAFFL`), and risk categorizations.
+  - `ADVS` (Vital Signs Analysis Dataset): Identifies baseline assessment (`BASE`), calculates post-baseline change (`CHG`), and percentage change (`PCHG`).
+  - `ADLB` (Laboratory Analysis Dataset): Baseline identification, change (`CHG`), and percentage change (`PCHG`).
+  - `ADAE` (Adverse Events Analysis Dataset): Numeric severity (`AESEVN`) and numerical causality mappings, treatment-emergent event flags (`TRTEMFL`).
+
+### Experiment 7: Statistical Analysis
+- **Objective**: Perform formal statistical hypothesis testing and inference.
+- **Tests Implemented**:
+  - Descriptive summary: N, Mean, SD, Median, IQR, Min, Max by treatment arm.
+  - Normality evaluation: Histograms, Q-Q plots, and Shapiro-Wilk tests.
+  - Variance homogeneity: Levene's test for equality of variances.
+  - Two-sample comparison: Independent t-test, mean differences, 95% confidence intervals, and Cohen's d effect size.
+  - Multi-group comparison: One-way ANOVA for SBP, DBP, and Glucose across all treatment arms.
+  - Post-hoc testing: Tukey's Honestly Significant Difference (HSD) test.
+  - Categorical association: Chi-square test and Fisher's exact test for adverse event incidence.
+
+### Experiment 8: Clinical Tables and Figures
+- **Objective**: Generate standard regulatory-style clinical trial tables and figures.
+- **Deliverables**:
+  - `table_14_1_1_demographics.csv`: Table 14.1.1 Summary of Demographics and Baseline Characteristics.
+  - `table_14_2_1_efficacy.csv`: Table 14.2.1 Summary of Change in Systolic Blood Pressure and Treatment Comparisons vs. Placebo.
+  - `table_14_3_1_adverse_events.csv`: Table 14.3.1 Overall Summary of Adverse Events by Severity and Preferred Term.
+  - `figure_14_2_1_sbp_boxplot.png`: Box plot of SBP change by treatment arm.
+  - `figure_14_2_2_forest_plot.png`: Forest plot illustrating treatment differences versus Placebo with 95% confidence intervals.
+
+---
+
+## Workflow Guide: Copying Code
+
+### Jupyter Notebook / Google Colab (Python)
+1. Run `rpstats.expX()` in a Python console or notebook cell (where `X` is 1 to 8).
+2. Copy the text printed under `---------------- PYTHON CODE ----------------`.
+3. Paste into a new Jupyter code cell and run.
+4. Ensure the required input CSV file is placed in your working directory.
+
+### RStudio / R Script (R Language)
+1. Run `rpstats.expX()` in Python to display the code.
+2. Copy the text printed under `---------------- R LANGUAGE CODE ----------------`.
+3. Open RStudio, create a new R Script (`File -> New File -> R Script`), and paste.
+4. Set your working directory using `setwd()` or place the input CSV in the R working directory, then execute the script.
+
+---
+
+## Requirements & Compatibility
+
+- **rpstats Package Runtime**:
+  - Python: `>= 3.8` (tested on 3.8, 3.9, 3.10, 3.11, 3.12, 3.13)
+  - Operating Systems: Windows, macOS, Linux
+  - No external runtime dependencies required to install or display code.
+
+- **To Execute Printed Python Scripts**:
+  - `pandas`, `numpy`, `matplotlib`, `seaborn`, `scipy`, `statsmodels`
+  - Install via: `pip install pandas numpy matplotlib seaborn scipy statsmodels`
+
+- **To Execute Printed R Scripts**:
+  - R `>= 4.0`
+  - Packages: `tidyverse`, `ggplot2`
+  - Install in R via: `install.packages(c("tidyverse", "ggplot2"))`
+
+---
+
+## License
+
+Distributed under the [MIT License](LICENSE).
+

rpstats-1.0.0/README.md

@@ -0,0 +1,193 @@
+# rpstats
+
+[![PyPI Version](https://img.shields.io/badge/pypi-v1.0.0-blue.svg)](https://pypi.org/project/rpstats/)
+[![Python Versions](https://img.shields.io/badge/python-3.8%20|%203.9%20|%203.10%20|%203.11%20|%203.12%20|%203.13-blue.svg)](https://pypi.org/project/rpstats/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+
+**rpstats** (*Reproducible Practical Statistics*) is a lightweight, professional Python package designed for biostatistics students, clinical data programmers, and researchers preparing for practical examinations and laboratory coursework.
+
+It contains **8 complete clinical data programming and statistical analysis practical experiments**, providing complete, clean, practical-ready code in **both Python and R**.
+
+---
+
+## Key Features
+
+- **Dual-Language Practical Code**: Instant access to complete, tested implementations in Python and R for every experiment.
+- **Zero Heavy Dependencies**: Installs instantly without requiring pandas, NumPy, SciPy, or R. Runs on any computer, standard college laboratory workstation, or laptop.
+- **Exam & Laboratory Ready**: Formatted for quick copy-pasting directly into Jupyter Notebook, Google Colab, or RStudio.
+- **Statistically & Clinically Sound**: Follows industry standards including CDISC SDTM / ADaM dataset architecture, standard clinical blood pressure guidelines, and statistical testing methodologies.
+
+---
+
+## Installation
+
+### Standard Installation (via PyPI)
+
+```bash
+pip install rpstats
+```
+
+### Local Development Installation
+
+Install in editable mode from the project directory:
+
+```bash
+pip install -e .
+```
+
+---
+
+## Quick Start & Usage
+
+Import the package in Python or inside a Jupyter Notebook:
+
+```python
+import rpstats
+
+# 1. Display package version
+rpstats.version()
+
+# 2. View the catalog of all 8 experiments
+rpstats.help()
+
+# 3. Print complete Python & R programs for any experiment
+rpstats.exp1()  # Data Import and Exploration
+rpstats.exp2()  # Data Cleaning
+rpstats.exp3()  # Data Transformation
+rpstats.exp4()  # Data Visualization
+rpstats.exp5()  # SDTM Dataset Creation
+rpstats.exp6()  # ADaM Dataset Creation
+rpstats.exp7()  # Statistical Analysis
+rpstats.exp8()  # Clinical Tables and Figures
+```
+
+---
+
+## Experiments Catalog
+
+| Function | Experiment Title | Input Files | Primary Output Files |
+| :--- | :--- | :--- | :--- |
+| `rpstats.exp1()` | **Data Import and Exploration** | `clinical_data.csv` | Terminal inspection output |
+| `rpstats.exp2()` | **Data Cleaning** | `clinical_trial_data_raw.csv` | `clinical_trial_data_cleaned.csv` |
+| `rpstats.exp3()` | **Data Transformation** | `clinical_demographics.csv`, `clinical_vitals_labs.csv` | `clinical_trial_data_analysis.csv` |
+| `rpstats.exp4()` | **Data Visualization** | `clinical_visualization_data.csv` | 5 High-res PNG plots (`dpi=300`) |
+| `rpstats.exp5()` | **SDTM Dataset Creation** | 5 Raw clinical domains | `dm_sdtm.csv`, `vs_sdtm.csv`, `lb_sdtm.csv`, `ae_sdtm.csv`, `ex_sdtm.csv` |
+| `rpstats.exp6()` | **ADaM Dataset Creation** | 5 SDTM domains | `adsl.csv`, `advs.csv`, `adlb.csv`, `adae.csv` |
+| `rpstats.exp7()` | **Statistical Analysis** | `adam_exp7_analysis.csv` | `placebo_sbp_qqplot.png`, `statistical_analysis_results.csv` |
+| `rpstats.exp8()` | **Clinical Tables and Figures** | `adsl_exp8.csv`, `advs_exp8.csv`, `adae_exp8.csv` | Tables 14.1.1, 14.2.1, 14.3.1 (CSV), Figures 14.2.1, 14.2.2 (PNG) |
+
+---
+
+## Experiment Details
+
+### Experiment 1: Data Import and Exploration
+- **Objective**: Import and inspect clinical trial datasets.
+- **Python**: Uses `pandas` and `numpy` to display the first and last records, shape, column names, data types, summary statistics, and missing value counts.
+- **R**: Uses base R to inspect dimensions, structure (`str()`), column names, summary statistics, missing values per column, and complete case counts.
+
+### Experiment 2: Data Cleaning
+- **Objective**: Perform essential clinical data cleaning tasks.
+- **Key Operations**:
+  - Impute numeric missing values using column medians.
+  - Impute missing site identifiers (`SITEID`) with `"Unknown"`.
+  - Identify and remove exact duplicate rows.
+  - Deduplicate patient records (`USUBJID`), retaining the first record.
+  - Standardize patient sex into `'M'` and `'F'`.
+  - Save cleaned data to `clinical_trial_data_cleaned.csv`.
+
+### Experiment 3: Data Transformation
+- **Objective**: Merge demographics with clinical vitals/labs and derive key study indicators.
+- **Key Operations**:
+  - Verify subject identifier (`USUBJID`) uniqueness and merge datasets using an inner join.
+  - Derive age groups (`<65`, `>=65`).
+  - Derive clinical blood pressure categories (`Normal`, `Elevated`, `Stage 1 Hypertension`, `Stage 2 Hypertension`).
+  - Calculate days on study (`DAYS_ON_STUDY`) against a configurable cutoff date.
+  - Derive clinical high-risk flag (`HIGH_RISK_FLAG`).
+  - Save merged dataset as `clinical_trial_data_analysis.csv`.
+
+### Experiment 4: Clinical Data Visualization
+- **Objective**: Generate publication-grade, high-resolution figures.
+- **Figures Generated**:
+  1. `age_histogram.png`: Age distribution with kernel density curve.
+  2. `sex_barchart.png`: Subject count by sex.
+  3. `bmi_by_agegroup_boxplot.png`: BMI distribution grouped by age category.
+  4. `glucose_by_arm_histogram.png`: Fasting glucose distribution across treatment arms.
+  5. `height_weight_scatterplot.png`: Height vs. weight scatter plot categorized by sex.
+
+### Experiment 5: SDTM Dataset Creation
+- **Objective**: Transform raw source data into standardized CDISC SDTM domain structures.
+- **Domains Produced**:
+  - `DM` (Demographics): Subject identifiers, age, sex, race, treatment arm, date ISO standardizations.
+  - `VS` (Vital Signs): Wide-to-long transformation of SYSBP, DIABP, PULSE, and TEMP with sequence numbering (`VSSEQ`).
+  - `LB` (Laboratory): Wide-to-long transformation of GLUC, ALT, AST, and BILI with sequence numbering (`LBSEQ`).
+  - `AE` (Adverse Events): Standardized severity (`MILD`, `MODERATE`, `SEVERE`), start/end dates, sequence numbering (`AESEQ`).
+  - `EX` (Exposure): Standardized treatment dosing records and sequence numbering (`EXSEQ`).
+
+### Experiment 6: ADaM Dataset Creation
+- **Objective**: Build CDISC ADaM datasets for statistical analysis.
+- **Datasets Produced**:
+  - `ADSL` (Subject-Level Analysis Dataset): Incorporates exposure metrics, treatment start/end dates, safety population flag (`SAFFL`), and risk categorizations.
+  - `ADVS` (Vital Signs Analysis Dataset): Identifies baseline assessment (`BASE`), calculates post-baseline change (`CHG`), and percentage change (`PCHG`).
+  - `ADLB` (Laboratory Analysis Dataset): Baseline identification, change (`CHG`), and percentage change (`PCHG`).
+  - `ADAE` (Adverse Events Analysis Dataset): Numeric severity (`AESEVN`) and numerical causality mappings, treatment-emergent event flags (`TRTEMFL`).
+
+### Experiment 7: Statistical Analysis
+- **Objective**: Perform formal statistical hypothesis testing and inference.
+- **Tests Implemented**:
+  - Descriptive summary: N, Mean, SD, Median, IQR, Min, Max by treatment arm.
+  - Normality evaluation: Histograms, Q-Q plots, and Shapiro-Wilk tests.
+  - Variance homogeneity: Levene's test for equality of variances.
+  - Two-sample comparison: Independent t-test, mean differences, 95% confidence intervals, and Cohen's d effect size.
+  - Multi-group comparison: One-way ANOVA for SBP, DBP, and Glucose across all treatment arms.
+  - Post-hoc testing: Tukey's Honestly Significant Difference (HSD) test.
+  - Categorical association: Chi-square test and Fisher's exact test for adverse event incidence.
+
+### Experiment 8: Clinical Tables and Figures
+- **Objective**: Generate standard regulatory-style clinical trial tables and figures.
+- **Deliverables**:
+  - `table_14_1_1_demographics.csv`: Table 14.1.1 Summary of Demographics and Baseline Characteristics.
+  - `table_14_2_1_efficacy.csv`: Table 14.2.1 Summary of Change in Systolic Blood Pressure and Treatment Comparisons vs. Placebo.
+  - `table_14_3_1_adverse_events.csv`: Table 14.3.1 Overall Summary of Adverse Events by Severity and Preferred Term.
+  - `figure_14_2_1_sbp_boxplot.png`: Box plot of SBP change by treatment arm.
+  - `figure_14_2_2_forest_plot.png`: Forest plot illustrating treatment differences versus Placebo with 95% confidence intervals.
+
+---
+
+## Workflow Guide: Copying Code
+
+### Jupyter Notebook / Google Colab (Python)
+1. Run `rpstats.expX()` in a Python console or notebook cell (where `X` is 1 to 8).
+2. Copy the text printed under `---------------- PYTHON CODE ----------------`.
+3. Paste into a new Jupyter code cell and run.
+4. Ensure the required input CSV file is placed in your working directory.
+
+### RStudio / R Script (R Language)
+1. Run `rpstats.expX()` in Python to display the code.
+2. Copy the text printed under `---------------- R LANGUAGE CODE ----------------`.
+3. Open RStudio, create a new R Script (`File -> New File -> R Script`), and paste.
+4. Set your working directory using `setwd()` or place the input CSV in the R working directory, then execute the script.
+
+---
+
+## Requirements & Compatibility
+
+- **rpstats Package Runtime**:
+  - Python: `>= 3.8` (tested on 3.8, 3.9, 3.10, 3.11, 3.12, 3.13)
+  - Operating Systems: Windows, macOS, Linux
+  - No external runtime dependencies required to install or display code.
+
+- **To Execute Printed Python Scripts**:
+  - `pandas`, `numpy`, `matplotlib`, `seaborn`, `scipy`, `statsmodels`
+  - Install via: `pip install pandas numpy matplotlib seaborn scipy statsmodels`
+
+- **To Execute Printed R Scripts**:
+  - R `>= 4.0`
+  - Packages: `tidyverse`, `ggplot2`
+  - Install in R via: `install.packages(c("tidyverse", "ggplot2"))`
+
+---
+
+## License
+
+Distributed under the [MIT License](LICENSE).
+

rpstats-1.0.0/pyproject.toml

@@ -0,0 +1,53 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "rpstats"
+version = "1.0.0"
+description = "Clinical Data Programming and Statistical Analysis Practical Code Library."
+readme = "README.md"
+requires-python = ">=3.8"
+license = "MIT"
+keywords = [
+    "clinical-trials",
+    "biostatistics",
+    "clinical-data-programming",
+    "cdisc",
+    "sdtm",
+    "adam",
+    "pharmaceutical",
+    "r-programming",
+    "data-science",
+    "statistics"
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Education",
+    "Intended Audience :: Healthcare Industry",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: R",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Topic :: Scientific/Engineering :: Medical Science Apps.",
+    "Topic :: Scientific/Engineering :: Mathematics"
+]
+dependencies = []
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0",
+    "build",
+    "twine"
+]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["rpstats*"]

rpstats-1.0.0/rpstats/__init__.py

@@ -0,0 +1,62 @@
+"""rpstats: Clinical Data Programming and Statistical Analysis Practical Code Library.
+
+Provides complete, short, practical-ready code for 8 clinical data programming
+and biostatistical analysis practical experiments in both Python and R.
+"""
+
+from .exp1 import exp1
+from .exp2 import exp2
+from .exp3 import exp3
+from .exp4 import exp4
+from .exp5 import exp5
+from .exp6 import exp6
+from .exp7 import exp7
+from .exp8 import exp8
+
+__version__ = "1.0.0"
+
+_EXPERIMENTS = [
+    ("exp1()", "Data Import and Exploration"),
+    ("exp2()", "Data Cleaning"),
+    ("exp3()", "Data Transformation"),
+    ("exp4()", "Data Visualization"),
+    ("exp5()", "SDTM Dataset Creation"),
+    ("exp6()", "ADaM Dataset Creation"),
+    ("exp7()", "Statistical Analysis"),
+    ("exp8()", "Clinical Tables and Figures"),
+]
+
+
+def help() -> None:
+    """Display the list of all practical experiments available in rpstats."""
+    sep = "=" * 65
+    print(sep)
+    print("rpstats - Clinical Data Programming & Statistics Experiments")
+    print(sep)
+    print("Call any function below to print complete Python and R code:\n")
+    for func, title in _EXPERIMENTS:
+        print(f"  rpstats.{func:<10} : {title}")
+    print(f"\nPackage version: {__version__}")
+    print("Use help(rpstats.<func>) for more details on each experiment.")
+    print(sep)
+
+
+def version() -> None:
+    """Display the installed rpstats package version."""
+    print(f"rpstats version {__version__}")
+
+
+__all__ = [
+    "exp1",
+    "exp2",
+    "exp3",
+    "exp4",
+    "exp5",
+    "exp6",
+    "exp7",
+    "exp8",
+    "help",
+    "version",
+    "__version__",
+]
+

rpstats-1.0.0/rpstats/_display.py

@@ -0,0 +1,14 @@
+"""Display formatting utilities for rpstats practical experiments."""
+
+
+def display_experiment(exp_num: int, title: str, python_code: str, r_code: str) -> None:
+    """Print standard formatted output for an experiment in both Python and R."""
+    sep = "=" * 55
+    print(sep)
+    print(f"EXPERIMENT {exp_num}: {title.upper()}")
+    print(sep)
+    print("\n---------------- PYTHON CODE ----------------\n")
+    print(python_code.strip())
+    print("\n---------------- R LANGUAGE CODE ----------------\n")
+    print(r_code.strip())
+

rpstats-1.0.0/rpstats/exp1.py

@@ -0,0 +1,86 @@
+"""Experiment 1: Data Import and Exploration."""
+
+from ._display import display_experiment
+
+PYTHON_CODE = r'''import pandas as pd
+import numpy as np
+
+# 1. Read the CSV file
+df = pd.read_csv("clinical_data.csv")
+
+# 2. Display first 5 records
+print("--- First 5 Records ---")
+print(df.head())
+
+# 3. Display last 5 records
+print("\n--- Last 5 Records ---")
+print(df.tail())
+
+# 4. Display dataset shape
+print(f"\nDataset Shape (Rows, Columns): {df.shape}")
+
+# 5. Display column names
+print("\n--- Column Names ---")
+print(df.columns.tolist())
+
+# 6. Display data types
+print("\n--- Data Types ---")
+print(df.dtypes)
+
+# 7. Generate descriptive statistics
+print("\n--- Descriptive Statistics ---")
+print(df.describe(include="all"))
+
+# 8. Check missing values per column
+print("\n--- Missing Values Count ---")
+print(df.isnull().sum())
+
+# 9. Display dataset information
+print("\n--- Dataset Info ---")
+df.info()
+'''
+
+R_CODE = r'''# 1. Set working directory (adjust path as needed)
+setwd(getwd())
+
+# 2. Read the CSV file
+df <- read.csv("clinical_data.csv", stringsAsFactors = FALSE)
+
+# 3. Display first 6 records
+cat("--- First 6 Records ---\n")
+print(head(df))
+
+# 4. Display last 6 records
+cat("\n--- Last 6 Records ---\n")
+print(tail(df))
+
+# 5. Display dimensions (Rows, Columns)
+cat("\n--- Dataset Dimensions ---\n")
+print(dim(df))
+
+# 6. Display column names
+cat("\n--- Column Names ---\n")
+print(colnames(df))
+
+# 7. Display structure
+cat("\n--- Dataset Structure ---\n")
+str(df)
+
+# 8. Generate summary statistics
+cat("\n--- Summary Statistics ---\n")
+print(summary(df))
+
+# 9. Check missing values per column
+cat("\n--- Missing Values Count ---\n")
+print(colSums(is.na(df)))
+
+# 10. Count complete cases
+complete_count <- sum(complete.cases(df))
+cat(sprintf("\nComplete Cases: %d out of %d\n", complete_count, nrow(df)))
+'''
+
+
+def exp1() -> None:
+    """Print complete Python and R programs for Experiment 1."""
+    display_experiment(1, "Data Import and Exploration", PYTHON_CODE, R_CODE)
+