CBCgrpspy 0.3

Statistical Group Comparison Tool

📊 Data Analysis Toolkit

Automated comparative analysis tool for group data, supporting intelligent statistical tests for two/multiple groups with standardized output tables.

⚙️ Installation

pip install CBCgrpspy 

---

📖 Parameter Specifications

Parameter	Type	Default	Description
df_path	str	Required	Data file path (.xlsx/.csv supported)
label_series	str	"label"	Target label column name (must specify if no "label" column exists)
skewvaranalysis	list	None	Manually specified categorical variables
norm_rd	int	2	Decimal places for normal distributions (Mean ± SD format)
sk_rd	int	2	Decimal places for non-normal distributions (Median (IQR) format)
cat_rd	int	0	Decimal places for categorical variable percentages
pnormtest	float	0.05	Significance threshold for normality tests
phomogeneity	float	0.05	Significance threshold for homogeneity of variance tests
extractp	float	0.05	Threshold for identifying significant variables
minfactorlevels	int	10	Maximum categorical levels (variables exceeding this become continuous)
showstatistic	bool	True	Whether to display statistical values in output

---

🚀 Core Features

1. Two-Group Comparison (Binary Groups)

• Use Cases: Control vs Treatment, Male vs Female, etc.
• Statistical Methods:
  • 📌 Continuous variables: Auto-select T-test / Mann-Whitney U test
  • 📌 Categorical variables: Auto-select Chi-square / Fisher's exact test
• Output:
  • Standardized comparison table
  • Flagged significant variables (p < extractp)

2. Multi-Group Comparison (≥3 Groups)

• Use Cases: Age stratification, multiple treatment protocols, etc.
• Statistical Methods:
  • 📌 Continuous variables: ANOVA / Kruskal-Wallis test
  • 📌 Categorical variables: Chi-square / Monte Carlo Fisher simulation
• Output:
  • Multi-dimensional group comparison summary
  • Subgroup difference indicators

---

🎯 Quick Start Example

from CBCgrpspy import dataAnalysis

result = dataAnalysis(
    df_path="analysis.xlsx",
    label_series="label",
    norm_rd=2,
    sk_rd=2,
    cat_rd=0,
    pnormtest=0.05,
    extractp=0.05,
    phomogeneity=0.05,
    maxfactorlevels=10,
    showstatistic=True
)

print(result["comparison_table"])    # Output comparison matrix
print(result["significant_vars"])    # List of significant variables

---

📌 Important Notes

1. Ensure the first row contains column headers
2. Convert categorical variables to string type beforehand
3. Recommended for use with Jupyter Notebook for optimal table rendering
4. This package has currently only been tested on Windows 10/11 systems. Compatibility with macOS and Linux systems has not been verified.

---

💡 Pro Tip: Adjust *_rd parameters to control decimal precision. Use showstatistic=False for simplified outputs.