lasmnemonicsid 0.0.3rc0__tar.gz → 0.0.5__tar.gz

lasmnemonicsid-0.0.5/PKG-INFO

@@ -0,0 +1,276 @@
+Metadata-Version: 2.4
+Name: lasmnemonicsid
+Version: 0.0.5
+Summary: Well log mnemonic identification using lasio and dlisio to load LAS/DLIS/ASCII files into DataFrames
+Author-email: Nobleza Energy <info@nobleza-energy.com>
+License: MIT
+Project-URL: Homepage, https://nobleza-energy.github.io/LASMnemonicsID
+Project-URL: Repository, https://github.com/Nobleza-Energy/LASMnemonicsID
+Project-URL: Documentation, https://nobleza-energy.github.io/LASMnemonicsID/
+Project-URL: Bug Tracker, https://github.com/Nobleza-Energy/LASMnemonicsID/issues
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.21.0
+Requires-Dist: pandas>=2.0.1
+Requires-Dist: lasio>=0.30
+Requires-Dist: dlisio>=1.0.0
+Provides-Extra: docs
+Requires-Dist: mkdocs>=1.5.0; extra == "docs"
+Requires-Dist: mkdocs-material>=9.0.0; extra == "docs"
+Requires-Dist: mkdocstrings[python]>=0.24.0; extra == "docs"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: isort>=5.12.0; extra == "dev"
+Requires-Dist: flake8>=6.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Dynamic: license-file
+
+# LASMnemonicsID
+
+<p align="center">
+  <img src="https://github.com/Nobleza-Energy/LASMnemonicsID/blob/e44bfb606fef5cfc9c3df6e41c3d1bd0d7bb08ae/logo.png?raw=true" alt="LASMnemonicsID Logo" width="200"/>
+</p>
+
+<p align="center">
+  <b>Well log mnemonic identification and standardization for LAS, DLIS, and ASCII formats</b>
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/lasmnemonicsid/"><img src="https://img.shields.io/pypi/v/lasmnemonicsid.svg" alt="PyPI"></a>
+  <a href="https://pypi.org/project/lasmnemonicsid/"><img src="https://img.shields.io/pypi/pyversions/lasmnemonicsid.svg" alt="Python Versions"></a>
+  <a href="https://github.com/Nobleza-Energy/LASMnemonicsID/blob/main/LICENSE"><img src="https://img.shields.io/github/license/Nobleza-Energy/LASMnemonicsID.svg" alt="License"></a>
+</p>
+
+---
+
+## Features
+
+- **Multi-format support**: LAS, DLIS, ASCII/CSV/TXT/DAT
+- **Automatic mnemonic standardization**: GR, RHOB, NPHI, DT, SP, CALI, RT, etc.
+- **Batch processing**: Parse entire directories recursively
+- **Customizable naming**: Override default standard names
+- **Case-insensitive extensions**: Works with .las/.LAS, .dlis/.DLIS, .csv/.CSV, etc.
+- **Pandas integration**: Returns clean DataFrames ready for analysis
+
+---
+
+## Installation
+
+```bash
+pip install lasmnemonicsid
+```
+
+This installs support for **all formats** (LAS, DLIS, ASCII/CSV/TXT).
+
+---
+
+## Quick Start
+
+### LAS Files
+
+```python
+from LASMnemonicsID import parseLAS
+
+# Parse single LAS file
+df = parseLAS("well.las")
+print(df.head())
+
+# Parse directory
+data = parseLAS("/path/to/las/files/")
+for filename, df in data.items():
+    print(f"{filename}: {df.shape}")
+```
+
+### DLIS Files
+
+```python
+from LASMnemonicsID import parseDLIS
+
+# Parse single DLIS file
+df = parseDLIS("well.dlis")
+print(df.columns)
+
+# Parse directory
+data = parseDLIS("/path/to/dlis/files/")
+```
+
+### ASCII/CSV/TXT Files
+
+```python
+from LASMnemonicsID import parseASCII
+
+# Parse CSV
+df = parseASCII("well_log.csv", depth_col="DEPTH")
+
+# Parse tab-separated TXT
+df = parseASCII("well_log.txt", delimiter="\t")
+
+# Parse directory
+data = parseASCII("/path/to/csv/files/")
+```
+
+---
+
+## Advanced Usage
+
+### Custom Preferred Names
+
+```python
+preferred = {
+    "deepres": "RT",
+    "deepres_preferred_original": "AT90",
+    "gamma": "GR"
+}
+
+df = parseLAS("well.las", preferred_names=preferred)
+```
+
+### Batch Processing
+
+```python
+from pathlib import Path
+
+dir_path = Path("/data/wells/")
+data = parseLAS(dir_path, verbose=True, preferred_names=preferred)
+
+for fname, df in data.items():
+    print(f"{fname}: {df.shape}")
+    print(df.head(3))
+```
+
+### Mixed Format Directories
+
+```python
+las_data = parseLAS("/data/wells/")
+dlis_data = parseDLIS("/data/wells/")
+ascii_data = parseASCII("/data/wells/")
+
+all_data = {**las_data, **dlis_data, **ascii_data}
+```
+
+---
+
+## Supported Mnemonics
+
+The package automatically standardizes these curve types:
+
+| Curve Type | Standard Name | Example Aliases |
+|------------|---------------|-------------|
+| Gamma Ray | `GR` | gr, cggr, cgr, gam, gamma, gammaray, grc, grd, hgr, sgr, lgr, pgr |
+| Spontaneous Potential | `SP` | sp, idsp, spr, spl, spdl, spdhp, spc, sp0, sp1, cgsp, dlsp |
+| Caliper | `CALI` | caliper, calip, cal, dcal, acal, cala, cald, cale, calh, hcal, xcal, ycal |
+| Deep Resistivity | `RT` | rt, rtao, rt90, ild, idph, rild, rd, ae90, at90, atrt, lld, lldc, res, resd |
+| Shallow Resistivity | `RXO` | rxo, rxoz, msfl, mcfl, sflcc, mgl, m1rx, r40o, aht10 |
+| Density | `RHOB` | rhob, rhoz, den, denb, denc, hrho, hrhob, zden, hden, denf, denn |
+| Density Correction | `DRHO` | dcor, dcorr, dc, decr, drh, zcor, zcorr, hhdr, denscorr |
+| Neutron Porosity | `NPHI` | cn, phin, cnc, cns, hnphi, nphi, npor, cncc, nprl, neut, neutpor |
+| Sonic (Compressional) | `DT` | dt, dtc, dtco, dtcomp, deltat, slow, slowness, tt, ac, acco, delt, dtcomp |
+| Sonic (Shear) | `DTS` | dts, dtsh, dtsm, dtsc, dtsd, dtsqi, dtshear, deltas, tts, stt, dtshear |
+| Photoelectric Factor | `PEF` | pe, pef, pefz, pdpe, pedf, pedn, hpedn, pe2, pef8, lpe |
+
+
+---
+
+## Testing
+
+```bash
+pytest tests/ -v
+pytest tests/test_las.py -v
+pytest tests/test_dlis.py -v
+pytest tests/test_ascii.py -v
+```
+
+---
+
+## API Reference
+
+### parseLAS(input_path, verbose=True, preferred_names=None)
+
+Parse LAS file(s) and standardize mnemonics.
+
+**Parameters:**
+- input_path (str/Path): LAS file or directory
+- verbose (bool): Print parsing info
+- preferred_names (dict): Custom name mappings
+
+**Returns:** DataFrame (single file) or dict (multiple files)
+
+### parseDLIS(input_path, verbose=True, preferred_names=None)
+
+Parse DLIS file(s) and standardize mnemonics.
+
+**Parameters:**
+- input_path (str/Path): DLIS file or directory
+- verbose (bool): Print parsing info
+- preferred_names (dict): Custom name mappings
+
+**Returns:** DataFrame (single file) or dict (multiple files)
+
+### parseASCII(input_path, verbose=True, preferred_names=None, depth_col="DEPTH", delimiter=",")
+
+Parse ASCII/CSV/TXT file(s) and standardize mnemonics.
+
+**Parameters:**
+- input_path (str/Path): ASCII file or directory
+- verbose (bool): Print parsing info
+- preferred_names (dict): Custom name mappings
+- depth_col (str): Name of depth column
+- delimiter (str): Field separator
+
+**Returns:** DataFrame (single file) or dict (multiple files)
+
+---
+
+## How to Cite
+
+**APA**
+
+> Nobleza Energy. (2026). LASMnemonicsID: Well log mnemonic identification for LAS, DLIS, and ASCII formats [Software]. GitHub. https://github.com/Nobleza-Energy/LASMnemonicsID
+
+**BibTeX**
+
+```bibtex
+@software{LASMnemonicsID,
+  author = {Nobleza Energy},
+  title = {LASMnemonicsID: Well log mnemonic identification for LAS, DLIS, and ASCII formats},
+  year = {2026},
+  publisher = {GitHub},
+  url = {https://github.com/Nobleza-Energy/LASMnemonicsID}
+}
+```
+
+---
+
+## License
+
+MIT License - see [LICENSE](LICENSE) file.
+
+---
+
+## Contributing
+
+Contributions welcome! Submit a Pull Request.
+
+---
+
+## Support
+
+- **Issues:** [GitHub Issues](https://github.com/Nobleza-Energy/LASMnemonicsID/issues)
+- **Discussions:** [GitHub Discussions](https://github.com/Nobleza-Energy/LASMnemonicsID/discussions)
+
+---
+
+<p align="center">
+  Made with ❤️ by <a href="https://nobleza-energy.com">Nobleza Energy</a>
+</p>

lasmnemonicsid-0.0.5/README.md

@@ -0,0 +1,238 @@
+# LASMnemonicsID
+
+<p align="center">
+  <img src="https://github.com/Nobleza-Energy/LASMnemonicsID/blob/e44bfb606fef5cfc9c3df6e41c3d1bd0d7bb08ae/logo.png?raw=true" alt="LASMnemonicsID Logo" width="200"/>
+</p>
+
+<p align="center">
+  <b>Well log mnemonic identification and standardization for LAS, DLIS, and ASCII formats</b>
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/lasmnemonicsid/"><img src="https://img.shields.io/pypi/v/lasmnemonicsid.svg" alt="PyPI"></a>
+  <a href="https://pypi.org/project/lasmnemonicsid/"><img src="https://img.shields.io/pypi/pyversions/lasmnemonicsid.svg" alt="Python Versions"></a>
+  <a href="https://github.com/Nobleza-Energy/LASMnemonicsID/blob/main/LICENSE"><img src="https://img.shields.io/github/license/Nobleza-Energy/LASMnemonicsID.svg" alt="License"></a>
+</p>
+
+---
+
+## Features
+
+- **Multi-format support**: LAS, DLIS, ASCII/CSV/TXT/DAT
+- **Automatic mnemonic standardization**: GR, RHOB, NPHI, DT, SP, CALI, RT, etc.
+- **Batch processing**: Parse entire directories recursively
+- **Customizable naming**: Override default standard names
+- **Case-insensitive extensions**: Works with .las/.LAS, .dlis/.DLIS, .csv/.CSV, etc.
+- **Pandas integration**: Returns clean DataFrames ready for analysis
+
+---
+
+## Installation
+
+```bash
+pip install lasmnemonicsid
+```
+
+This installs support for **all formats** (LAS, DLIS, ASCII/CSV/TXT).
+
+---
+
+## Quick Start
+
+### LAS Files
+
+```python
+from LASMnemonicsID import parseLAS
+
+# Parse single LAS file
+df = parseLAS("well.las")
+print(df.head())
+
+# Parse directory
+data = parseLAS("/path/to/las/files/")
+for filename, df in data.items():
+    print(f"{filename}: {df.shape}")
+```
+
+### DLIS Files
+
+```python
+from LASMnemonicsID import parseDLIS
+
+# Parse single DLIS file
+df = parseDLIS("well.dlis")
+print(df.columns)
+
+# Parse directory
+data = parseDLIS("/path/to/dlis/files/")
+```
+
+### ASCII/CSV/TXT Files
+
+```python
+from LASMnemonicsID import parseASCII
+
+# Parse CSV
+df = parseASCII("well_log.csv", depth_col="DEPTH")
+
+# Parse tab-separated TXT
+df = parseASCII("well_log.txt", delimiter="\t")
+
+# Parse directory
+data = parseASCII("/path/to/csv/files/")
+```
+
+---
+
+## Advanced Usage
+
+### Custom Preferred Names
+
+```python
+preferred = {
+    "deepres": "RT",
+    "deepres_preferred_original": "AT90",
+    "gamma": "GR"
+}
+
+df = parseLAS("well.las", preferred_names=preferred)
+```
+
+### Batch Processing
+
+```python
+from pathlib import Path
+
+dir_path = Path("/data/wells/")
+data = parseLAS(dir_path, verbose=True, preferred_names=preferred)
+
+for fname, df in data.items():
+    print(f"{fname}: {df.shape}")
+    print(df.head(3))
+```
+
+### Mixed Format Directories
+
+```python
+las_data = parseLAS("/data/wells/")
+dlis_data = parseDLIS("/data/wells/")
+ascii_data = parseASCII("/data/wells/")
+
+all_data = {**las_data, **dlis_data, **ascii_data}
+```
+
+---
+
+## Supported Mnemonics
+
+The package automatically standardizes these curve types:
+
+| Curve Type | Standard Name | Example Aliases |
+|------------|---------------|-------------|
+| Gamma Ray | `GR` | gr, cggr, cgr, gam, gamma, gammaray, grc, grd, hgr, sgr, lgr, pgr |
+| Spontaneous Potential | `SP` | sp, idsp, spr, spl, spdl, spdhp, spc, sp0, sp1, cgsp, dlsp |
+| Caliper | `CALI` | caliper, calip, cal, dcal, acal, cala, cald, cale, calh, hcal, xcal, ycal |
+| Deep Resistivity | `RT` | rt, rtao, rt90, ild, idph, rild, rd, ae90, at90, atrt, lld, lldc, res, resd |
+| Shallow Resistivity | `RXO` | rxo, rxoz, msfl, mcfl, sflcc, mgl, m1rx, r40o, aht10 |
+| Density | `RHOB` | rhob, rhoz, den, denb, denc, hrho, hrhob, zden, hden, denf, denn |
+| Density Correction | `DRHO` | dcor, dcorr, dc, decr, drh, zcor, zcorr, hhdr, denscorr |
+| Neutron Porosity | `NPHI` | cn, phin, cnc, cns, hnphi, nphi, npor, cncc, nprl, neut, neutpor |
+| Sonic (Compressional) | `DT` | dt, dtc, dtco, dtcomp, deltat, slow, slowness, tt, ac, acco, delt, dtcomp |
+| Sonic (Shear) | `DTS` | dts, dtsh, dtsm, dtsc, dtsd, dtsqi, dtshear, deltas, tts, stt, dtshear |
+| Photoelectric Factor | `PEF` | pe, pef, pefz, pdpe, pedf, pedn, hpedn, pe2, pef8, lpe |
+
+
+---
+
+## Testing
+
+```bash
+pytest tests/ -v
+pytest tests/test_las.py -v
+pytest tests/test_dlis.py -v
+pytest tests/test_ascii.py -v
+```
+
+---
+
+## API Reference
+
+### parseLAS(input_path, verbose=True, preferred_names=None)
+
+Parse LAS file(s) and standardize mnemonics.
+
+**Parameters:**
+- input_path (str/Path): LAS file or directory
+- verbose (bool): Print parsing info
+- preferred_names (dict): Custom name mappings
+
+**Returns:** DataFrame (single file) or dict (multiple files)
+
+### parseDLIS(input_path, verbose=True, preferred_names=None)
+
+Parse DLIS file(s) and standardize mnemonics.
+
+**Parameters:**
+- input_path (str/Path): DLIS file or directory
+- verbose (bool): Print parsing info
+- preferred_names (dict): Custom name mappings
+
+**Returns:** DataFrame (single file) or dict (multiple files)
+
+### parseASCII(input_path, verbose=True, preferred_names=None, depth_col="DEPTH", delimiter=",")
+
+Parse ASCII/CSV/TXT file(s) and standardize mnemonics.
+
+**Parameters:**
+- input_path (str/Path): ASCII file or directory
+- verbose (bool): Print parsing info
+- preferred_names (dict): Custom name mappings
+- depth_col (str): Name of depth column
+- delimiter (str): Field separator
+
+**Returns:** DataFrame (single file) or dict (multiple files)
+
+---
+
+## How to Cite
+
+**APA**
+
+> Nobleza Energy. (2026). LASMnemonicsID: Well log mnemonic identification for LAS, DLIS, and ASCII formats [Software]. GitHub. https://github.com/Nobleza-Energy/LASMnemonicsID
+
+**BibTeX**
+
+```bibtex
+@software{LASMnemonicsID,
+  author = {Nobleza Energy},
+  title = {LASMnemonicsID: Well log mnemonic identification for LAS, DLIS, and ASCII formats},
+  year = {2026},
+  publisher = {GitHub},
+  url = {https://github.com/Nobleza-Energy/LASMnemonicsID}
+}
+```
+
+---
+
+## License
+
+MIT License - see [LICENSE](LICENSE) file.
+
+---
+
+## Contributing
+
+Contributions welcome! Submit a Pull Request.
+
+---
+
+## Support
+
+- **Issues:** [GitHub Issues](https://github.com/Nobleza-Energy/LASMnemonicsID/issues)
+- **Discussions:** [GitHub Discussions](https://github.com/Nobleza-Energy/LASMnemonicsID/discussions)
+
+---
+
+<p align="center">
+  Made with ❤️ by <a href="https://nobleza-energy.com">Nobleza Energy</a>
+</p>

{lasmnemonicsid-0.0.3rc0 → lasmnemonicsid-0.0.5}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "lasmnemonicsid"
-version = "0.0.3c"  
-description = "Well log mnemonic identification using lasio and dlisio to load LAS/DLIS files into DataFrames"
+version = "0.0.5"  
+description = "Well log mnemonic identification using lasio and dlisio to load LAS/DLIS/ASCII files into DataFrames"
 readme = "README.md"
 authors = [
     {name = "Nobleza Energy", email = "info@nobleza-energy.com"}

lasmnemonicsid-0.0.5/src/LASMnemonicsID/ASCII/ASCII.py

@@ -0,0 +1,134 @@
+
+import LASMnemonicsID.utils.mnemonics as mnm
+from LASMnemonicsID.utils.mnemonics import (
+    gamma_names,
+    sp_names,
+    caliper_names,
+    deepres_names,
+    rxo_names,
+    density_names,
+    density_correction_names,
+    neutron_names,
+    dtc_names,
+    dts_names,
+    pe_names,
+)
+import os
+import pandas as pd
+from pathlib import Path
+
+# Import helper functions from LAS module
+from ..LAS.LAS import create_mnemonic_dict, _standardize_all_curves
+
+
+def parseASCII(input_path, verbose=True, preferred_names=None, depth_col="DEPTH", delimiter=","):
+    """
+    Parse ASCII/CSV/TXT well log file or all in directory → DataFrame or {filename: df}.
+    
+    Args:
+        input_path (str/Path): ASCII/CSV/TXT file or directory
+        verbose (bool): Print info
+        preferred_names (dict, optional): Mapping of curve types to preferred column names.
+            Example: {"deepres": "RT", "gamma": "GR"}
+            If not provided, defaults to standard petrophysical names.
+        depth_col (str): Name of depth column (default: "DEPTH")
+        delimiter (str): CSV delimiter (default: ",")
+        
+    Returns:
+        DataFrame (single) or dict {filename: df} (multiple/dir)
+    """
+    input_path = Path(input_path)
+    
+    # Define default standard names
+    std_names = {
+        "gamma": "GR",
+        "sp": "SP",
+        "caliper": "CALI",
+        "deepres": "RT",
+        "rxo": "RXO",
+        "density": "RHOB",
+        "density_correction": "DRHO",
+        "neutron": "NPHI",
+        "dtc": "DT",
+        "dts": "DTS",
+        "pe": "PEF"
+    }
+    
+    # Update with user preferences if provided
+    if preferred_names:
+        std_names.update(preferred_names)
+    
+    # All supported ASCII extensions (case-insensitive)
+    ascii_extensions = ['.csv', '.txt', '.asc', '.dat', '.ascii']
+    
+    # Case 1: Single File
+    if input_path.is_file() and input_path.suffix.lower() in ascii_extensions:
+        df = _read_single_ascii(input_path, verbose, std_names, depth_col, delimiter)
+        return df if df is not None else None
+    
+    # Case 2: Directory (Recursive) - CASE-INSENSITIVE
+    ascii_files = [f for f in input_path.rglob("*") if f.suffix.lower() in ascii_extensions]
+    if not ascii_files:
+        if verbose:
+            print(f"No ASCII/CSV files found in {input_path}")
+        return {}
+    
+    ascii_dict = {}
+    for ascii_file in ascii_files:
+        df = _read_single_ascii(ascii_file, verbose, std_names, depth_col, delimiter)
+        if df is not None:
+            filename = ascii_file.name
+            ascii_dict[filename] = df
+    
+    # Return single DF if only 1 file found, else dict
+    if len(ascii_dict) == 1:
+        return next(iter(ascii_dict.values()))
+    
+    return ascii_dict
+
+
+def _read_single_ascii(ascii_file_path, verbose, std_names, depth_col, delimiter):
+    """Read single ASCII/CSV file to DataFrame and standardize ALL curves."""
+    try:
+        # Try reading the file
+        df = pd.read_csv(ascii_file_path, delimiter=delimiter)
+        
+        if df.empty:
+            if verbose:
+                print(f"✗ Empty DataFrame: {ascii_file_path.name}")
+            return None
+        
+        # Handle depth column (case-insensitive)
+        depth_cols = [col for col in df.columns if col.upper() == depth_col.upper()]
+        if depth_cols:
+            df.set_index(depth_cols[0], inplace=True)
+        else:
+            # Use first column as depth
+            df.set_index(df.columns[0], inplace=True)
+        
+        # Ensure index is float
+        df.index = df.index.astype(float)
+        df.index.name = "DEPTH"
+        
+        # Create fake las_data object for standardization
+        class FakeLASData:
+            pass
+        
+        fake_las = FakeLASData()
+        
+        # Standardize ALL curves (GR, RHOB, NPHI, etc.)
+        _standardize_all_curves(fake_las, df, std_names)
+        
+        if verbose:
+            print(f"✓ {ascii_file_path.name}")
+        return df
+        
+    except Exception as e:
+        if verbose:
+            print(f"✗ Error in {ascii_file_path.name}: {type(e).__name__}: {e}")
+    return None
+
+
+def _get_well_name(ascii_file_path):
+    """Extract well name from ASCII file (use filename)"""
+    return ascii_file_path.stem

lasmnemonicsid-0.0.5/src/LASMnemonicsID/ASCII/__init__.py

@@ -0,0 +1,2 @@
+
+from .ASCII import *