Metadata-Version: 2.1
Name: quickstats
Version: 0.4.1
Summary: A tool for quick statistical analysis for HEP experiments
Home-page: UNKNOWN
Author: Alkaid Cheng
Author-email: chi.lung.cheng@cern.ch
License: UNKNOWN
Description: ## Setup
        
        Clone the repository:
        ```
        git clone ssh://git@gitlab.cern.ch:7999/clcheng/quickstats.git
        ```
        
        To setup:
        ```
        source setup.sh
        ```
        
        For the first time:
        ```
        quickstats compile
        ```
        
        ## Run Pulls
        ```
        quickstats run_pulls -i <input_ws_path> -d <dataset_name> -p <np_name/pattern> --poi <poi_name> --parallel -1 -o <output_dir>
        ```
        
        The following options are available
        
        | **Option** | **Description** | **Default** |
        | ---------- | ---------- | ----------- | 
        | `-i/--input_file` | Path to the input workspace file | - |
        | `-w/--workspace` | Name of workspace. Auto-detect by default. | None |
        | `-m/--model_config` | Name of model config. Auto-detect by default. | None |
        | `-d/--data` | Name of dataset | "combData" |
        | `-p/--parameter` | Nuisance parameter(s) to run pulls on. Multiple parameters are separated by commas. Wildcards are accepted. All NPs will be run over by default| "" |
        | `-x/--poi` | POIs to measure. If empty, impact on POI will not be calculated. | "" |
        | `-r/--profile` | Parameters to profile | "" |
        | `-f/--fix` | Parameters to fix | "" |
        | `-s/--snapshot` | Name of initial snapshot | "nominalNuis" |
        | `-o/--outdir` | Output directory | "pulls" |
        | `-t/--minimizer_type` | Minimizer type | "Minuit2" |
        | `-a/--minimizer_algo` | Minimizer algorithm | "Migrad" |
        | `-c/--num_cpu` | Number of CPUs to use per parameter | 1 |
        | `--binned/--unbinned` | Whether to use binned likelihood | True |
        | `-q/--precision` | Precision for scan | 0.001 |
        | `-e/--eps` | Tolerance | 1.0 |
        | `-l/--log_level` | Log level | "INFO" |
        | `--eigen/--no-eigen` | Compute eigenvalues and vectors | False |
        | `--strategy`  | Default fit strategy | 0 |
        | `--fix-cache/--no-fix-cache` | Fix StarMomentMorph cache | True |
        | `--fix-multi/--no-fix-multi` |  Fix MultiPdf level 2 | True |
        | `--offset/--no-offset` | Offset likelihood | True |
        | `--optimize/--no-optimize` | Optimize constant terms | True |
        | `--max_calls` | Maximum number of function calls | -1 |
        | `--max_iters` | Maximum number of Minuit iterations | -1 |
        | `--parallel` | Parallelize job across different nuisanceparameters using N workers. Use -1 for N_CPU workers. | 0 |
        | `--cache/--no-cache` | Cache existing result | True |
        | `--exclude` | Exclude NPs (wildcard is accepted) | "" |
        
        ## Plot Pulls
        
        ```
        quickstats plot_pulls --help
        ```
        
        ## Run Likelihood Scan
        
        ```
        quickstats likelihood_scan --help
        ```
        
        ## Inspect Workspace
        
        ```
        quickstats inspect_ws --help
        ```
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
