midiharmony 26.1.27__py3-none-any.whl → 26.1.30__py3-none-any.whl

midiharmony/README.md

@@ -13,17 +13,138 @@
 
 ## Install
 
+### Standard processing on CPU (default)
+
 ```sh
 !pip install -U midiharmony
 ```
 
+### Accelerated processing on GPU
+
+```sh
+!pip install -U midiharmony[gpu]
+```
+
 ***
 
-## Basic use example
+## Basic use examples
+*Using midiharmony is easy and requires just two lines of code :)*
+
+### Analyze a single MIDI
 
 ```python
 import midiharmony
+
+midi_harmony_dict = midiharmony.analyze_midi('Come To My Window.mid')
+
+# This code will return a single dictionary with harmony stats
+{'midi_path': 'Come To My Window.mid',
+  'midi_name': 'Come To My Window',
+  'total_chords_count': 2287,
+  'bad_chords_count': 11,
+  'grouped_chords_count': 1861,
+  'total_quads_count': 1861,
+  'unique_quads_count': 644,
+  'harmonic_quads_count': 470,
+  'harmony_ratio': 0.7298136645962733
+}
 ```
 
+### Analyze MIDI folder(s)
+
+```python
+import midiharmony
+
+midi_harmony_dicts_list = midiharmony.analyze_midi_folders(['./midi_folder_1',
+                                                            './midi_folder_2',
+                                                            './midi_folder_3'
+                                                           ])
+
+# This code will return a list of dictionaries with harmony stats
+# for all processed MIDIs from all specified folders
+[
+ {'midi_path': 'midi_folder_1/Bach Violin 2.mid',
+  'midi_name': 'Bach Violin 2',
+  'total_chords_count': 1089,
+  'bad_chords_count': 71,
+  'grouped_chords_count': 1045,
+  'total_quads_count': 1045,
+  'unique_quads_count': 974,
+  'harmonic_quads_count': 867,
+  'harmony_ratio': 0.8901437371663244},
+ {'midi_path': 'midi_folder_2/Camping at Aylm.mid',
+  'midi_name': 'Camping at Aylm',
+  'total_chords_count': 417,
+  'bad_chords_count': 7,
+  'grouped_chords_count': 383,
+  'total_quads_count': 383,
+  'unique_quads_count': 369,
+  'harmonic_quads_count': 326,
+  'harmony_ratio': 0.8834688346883469},
+ {'midi_path': 'midi_folder_3/Come To My Window.mid',
+  'midi_name': 'Come To My Window',
+  'total_chords_count': 2287,
+  'bad_chords_count': 11,
+  'grouped_chords_count': 1861,
+  'total_quads_count': 1861,
+  'unique_quads_count': 644,
+  'harmonic_quads_count': 470,
+  'harmony_ratio': 0.7298136645962733}
+]
+```
+
+***
+
+## NOTES
+
+* Most important value in each returned midi_harmony_dictionary is the "harmony_ratio"
+* High harmony_ratio (>=0.75) indicates good harmony
+* Exceptional harmony is indicated by harmony_ratio >= 0.9
+
+***
+
+## midiharmony API reference list
+
+```midiharmony.find_quads_fast_cupy```  
+*Count matching 4‑chord rows between two arrays using a GPU‑accelerated FNV‑1a hash.*
+
+```midiharmony.find_quads_fast_numpy```  
+*Count matching 4‑chord rows between two arrays using NumPy on CPU.*
+
+```midiharmony.get_trg_array```  
+*Load and cache the target harmonic‑quad array in NumPy or CuPy form.*
+
+```midiharmony.process_midi```  
+*Extract chords, grouped chords, and unique 4‑chord quads from a MIDI file.*
+
+```midiharmony.analyze_processed_midi```  
+*Compare extracted quads against the target database and compute harmony metrics.*
+
+```midiharmony.analyze_midi```  
+*Run the full pipeline: process a MIDI file and evaluate its harmonic quality.*
+
+```midiharmony.analyze_midi_folders```  
+*Batch‑analyze all MIDI files in one or more folders and return harmony reports.*
+
+```midiharmony.helpers.get_package_data```  
+*Return a sorted list of packaged `.npz` data files with their resolved paths.*
+
+```midiharmony.helpers.get_normalized_midi_md5_hash```  
+*Compute original and normalized MD5 hashes for any MIDI file.*
+
+```midiharmony.helpers.normalize_midi_file```  
+*Normalize a MIDI file and write the normalized version to disk.*
+
+```midiharmony.helpers.is_installed```  
+*Check whether a Debian package is installed using `dpkg-query`.*
+
+```midiharmony.helpers._run_apt_get```  
+*Internal helper to run `apt-get` commands with consistent flags and timeout.*
+
+```midiharmony.helpers.install_apt_package```  
+*Idempotently install an apt package with retries, optional sudo, and optional python‑apt.*
+
+***
+
 ### Project Los Angeles
 ### Tegridy Code 2026

midiharmony/midiharmony.py

@@ -62,8 +62,6 @@ print('=' * 70)
 
 import os, copy, time
 
-from typing import List, Optional, Union, Tuple, Dict, Any
-
 import tqdm
 
 ###################################################################################
@@ -157,8 +155,25 @@ def find_quads_fast_numpy(src_array: np.ndarray, trg_array: np.ndarray) -> int:
 _trg_cache_np = None
 _trg_cache_cp = None
 
-def get_trg_array(use_gpu=False, verbose=True):
+def get_trg_array(use_gpu: bool = False, verbose: bool = True):
     
+    """
+    Load and cache the target harmonic‑chord array in either NumPy (CPU) or CuPy (GPU) form.
+
+    Parameters
+    ----------
+    use_gpu : bool, optional
+        If True, return a cached CuPy array; otherwise return a cached NumPy array.
+        Falls back to NumPy automatically if CuPy is unavailable.
+    verbose : bool, optional
+        If True, print diagnostic messages when loading arrays for the first time.
+
+    Returns
+    -------
+    numpy.ndarray or cupy.ndarray
+        The cached target array, loaded once and reused across calls.
+    """
+
     global _trg_cache_np, _trg_cache_cp
 
     if not use_gpu:
@@ -191,9 +206,44 @@ def get_trg_array(use_gpu=False, verbose=True):
 
 ###################################################################################
 
-def process_midi(midi_file_path,
-                 verbose=True
-                ):
+def process_midi(midi_file_path: str, verbose: bool = True):
+    
+    """
+    Analyze a MIDI file and extract harmonic information, chord statistics,
+    and unique 4‑chord progression quads.
+
+    Parameters
+    ----------
+    midi_file_path : str
+        Path to the MIDI file to process.
+    verbose : bool, optional
+        If True, print progress messages and execution timing.
+
+    Returns
+    -------
+    dict
+        A dictionary containing:
+        
+        - 'midi_path' : str  
+            Original file path.
+        - 'midi_name' : str  
+            File name without extension.
+        - 'total_chords_count' : int  
+            Number of chordified events.
+        - 'bad_chords_count' : int  
+            Number of chords that required correction.
+        - 'grouped_chords_count' : int  
+            Length of the grouped chord sequence.
+        - 'total_quads_count' : int  
+            Total number of extracted 4‑chord windows.
+        - 'unique_quads_count' : int  
+            Number of unique 4‑chord quads.
+        - 'quads' : list[tuple[int]]  
+            Unique 4‑chord progressions discovered.
+
+        Returns an empty dictionary if the MIDI contains no events,
+        only drums, or an exception occurs.
+    """
 
     midi_name = os.path.splitext(os.path.basename(midi_file_path))[0]
 
@@ -351,9 +401,37 @@ def process_midi(midi_file_path,
 ###################################################################################
 
 def analyze_processed_midi(processed_midi_dict,
-                           keep_quads=False,
-                           verbose=False
+                           keep_quads: bool = False,
+                           verbose: bool = False
                           ):
+    
+    """
+    Evaluate harmonic quality of a processed MIDI file by comparing its
+    extracted chord‑quad sequences against the target quad database.
+
+    Parameters
+    ----------
+    processed_midi_dict : dict
+        Output dictionary from `process_midi`, containing extracted chord
+        information and a 'quads' list of 4‑chord progressions.
+    keep_quads : bool, optional
+        If True, preserve the original 'quads' list in the returned dictionary.
+        If False, omit it to reduce memory usage.
+    verbose : bool, optional
+        If True, print progress messages and timing information.
+
+    Returns
+    -------
+    dict
+        A dictionary containing the original processed‑MIDI metadata plus:
+        
+        - 'harmonic_quads_count' : int  
+            Number of quads that match entries in the target quad database.
+        - 'harmony_ratio' : float  
+            Fraction of matching quads relative to total quads.
+
+        If `keep_quads` is False, the 'quads' key is removed.
+    """
 
     if verbose:
 
@@ -418,9 +496,26 @@ def analyze_processed_midi(processed_midi_dict,
 
 ###################################################################################
 
-def analyze_midi(midi_file_path,
-                 verbose=True
-                ):
+def analyze_midi(midi_file_path: str, verbose: bool = True):
+    
+    """
+    End‑to‑end MIDI harmony analysis pipeline combining chord extraction
+    and harmonic‑quad evaluation.
+
+    Parameters
+    ----------
+    midi_file_path : str
+        Path to the MIDI file to analyze.
+    verbose : bool, optional
+        If True, print progress messages and total execution time.
+
+    Returns
+    -------
+    dict
+        The harmony‑analysis dictionary produced by `analyze_processed_midi`.
+        Returns an empty dictionary if processing fails or the MIDI contains
+        no analyzable harmonic content.
+    """
 
     processed_midi_dict = {}
     harmony_dict = {}
@@ -450,12 +545,35 @@ def analyze_midi(midi_file_path,
     
 ###################################################################################
 
-def analyze_midi_folder(midi_folders_paths_list,
-                        midi_files_extensions=['.mid', '.midi', '.kar'],
-                        show_progress_bar=True,
-                        verbose=False
-                       ):
+def analyze_midi_folders(midi_folders_paths_list,
+                         midi_files_extensions=['.mid', '.midi', '.kar'],
+                         show_progress_bar: bool = True,
+                         verbose: bool = False
+                        ):
     
+    """
+    Batch‑analyze all MIDI files inside one or more folders, producing
+    harmony‑analysis dictionaries for each valid file.
+
+    Parameters
+    ----------
+    midi_folders_paths_list : list[str]
+        List of folder paths to search for MIDI files.
+    midi_files_extensions : list[str], optional
+        File extensions to include when scanning folders.
+    show_progress_bar : bool, optional
+        If True, display a tqdm progress bar while processing files.
+    verbose : bool, optional
+        If True, print diagnostic information and timing details.
+
+    Returns
+    -------
+    list[dict]
+        A list of harmony‑analysis dictionaries, one per successfully
+        processed MIDI file. Files that fail processing or contain no
+        analyzable harmonic content are skipped.
+    """
+
     if verbose:
         start_time = time.time()
         

midiharmony-26.1.30.dist-info/METADATA

@@ -0,0 +1,194 @@
+Metadata-Version: 2.4
+Name: midiharmony
+Version: 26.1.30
+Summary: Fast, data‑driven harmony analysis for any MIDI file
+Author-email: Alex Lev <alexlev61@proton.me>
+Maintainer-email: Alex Lev <alexlev61@proton.me>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/asigalov61/midiharmony
+Project-URL: SoundCloud, https://soundcloud.com/aleksandr-sigalov-61/
+Project-URL: Documentation, https://github.com/asigalov61/midiharmony
+Project-URL: Issues, https://github.com/asigalov61/midiharmony/issues
+Project-URL: Discussions, https://github.com/asigalov61/midiharmony/discussions
+Project-URL: Dataset, https://huggingface.co/datasets/projectlosangeles/Discover-MIDI-Dataset
+Keywords: MIDI,MIDI harmony,harmony,symbolic music,music,music harmony,harmony analysis,harmonic analysis,music information retrieval,MIR,music discovery,music search,music quality,music metadata,music recommendation,research,musicology,music analysis
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Education
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+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: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Multimedia :: Sound/Audio :: MIDI
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Environment :: Console
+Classifier: Natural Language :: English
+Classifier: Typing :: Typed
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: tqdm
+Requires-Dist: matplotlib
+Requires-Dist: numpy==1.26.4
+Provides-Extra: gpu
+Requires-Dist: cupy-cuda12x; extra == "gpu"
+Requires-Dist: numpy==1.26.4; extra == "gpu"
+Dynamic: license-file
+
+# midiharmony
+## Fast, data‑driven harmony analysis for any MIDI file
+
+<img width="1024" height="1024" alt="midiharmony" src="https://github.com/user-attachments/assets/586cf022-ce06-4cea-bfdc-ffcf9b0365d1" />
+
+***
+
+## Abstract
+
+*midiharmony provides fast, stand‑alone harmony analysis for MIDI files by comparing their chord and note relationships against a high‑quality database of extracted chord quads. This approach enables reliable detection of strong harmonic structure, musically coherent progressions, and potential inconsistencies, making it a practical tool for music‑AI pipelines, composition analysis, and large‑scale MIDI processing.*
+
+***
+
+## Install
+
+### Standard processing on CPU (default)
+
+```sh
+!pip install -U midiharmony
+```
+
+### Accelerated processing on GPU
+
+```sh
+!pip install -U midiharmony[gpu]
+```
+
+***
+
+## Basic use examples
+*Using midiharmony is easy and requires just two lines of code :)*
+
+### Analyze a single MIDI
+
+```python
+import midiharmony
+
+midi_harmony_dict = midiharmony.analyze_midi('Come To My Window.mid')
+
+# This code will return a single dictionary with harmony stats
+{'midi_path': 'Come To My Window.mid',
+  'midi_name': 'Come To My Window',
+  'total_chords_count': 2287,
+  'bad_chords_count': 11,
+  'grouped_chords_count': 1861,
+  'total_quads_count': 1861,
+  'unique_quads_count': 644,
+  'harmonic_quads_count': 470,
+  'harmony_ratio': 0.7298136645962733
+}
+```
+
+### Analyze MIDI folder(s)
+
+```python
+import midiharmony
+
+midi_harmony_dicts_list = midiharmony.analyze_midi_folders(['./midi_folder_1',
+                                                            './midi_folder_2',
+                                                            './midi_folder_3'
+                                                           ])
+
+# This code will return a list of dictionaries with harmony stats
+# for all processed MIDIs from all specified folders
+[
+ {'midi_path': 'midi_folder_1/Bach Violin 2.mid',
+  'midi_name': 'Bach Violin 2',
+  'total_chords_count': 1089,
+  'bad_chords_count': 71,
+  'grouped_chords_count': 1045,
+  'total_quads_count': 1045,
+  'unique_quads_count': 974,
+  'harmonic_quads_count': 867,
+  'harmony_ratio': 0.8901437371663244},
+ {'midi_path': 'midi_folder_2/Camping at Aylm.mid',
+  'midi_name': 'Camping at Aylm',
+  'total_chords_count': 417,
+  'bad_chords_count': 7,
+  'grouped_chords_count': 383,
+  'total_quads_count': 383,
+  'unique_quads_count': 369,
+  'harmonic_quads_count': 326,
+  'harmony_ratio': 0.8834688346883469},
+ {'midi_path': 'midi_folder_3/Come To My Window.mid',
+  'midi_name': 'Come To My Window',
+  'total_chords_count': 2287,
+  'bad_chords_count': 11,
+  'grouped_chords_count': 1861,
+  'total_quads_count': 1861,
+  'unique_quads_count': 644,
+  'harmonic_quads_count': 470,
+  'harmony_ratio': 0.7298136645962733}
+]
+```
+
+***
+
+## NOTES
+
+* Most important value in each returned midi_harmony_dictionary is the "harmony_ratio"
+* High harmony_ratio (>=0.75) indicates good harmony
+* Exceptional harmony is indicated by harmony_ratio >= 0.9
+
+***
+
+## midiharmony API reference list
+
+```midiharmony.find_quads_fast_cupy```  
+*Count matching 4‑chord rows between two arrays using a GPU‑accelerated FNV‑1a hash.*
+
+```midiharmony.find_quads_fast_numpy```  
+*Count matching 4‑chord rows between two arrays using NumPy on CPU.*
+
+```midiharmony.get_trg_array```  
+*Load and cache the target harmonic‑quad array in NumPy or CuPy form.*
+
+```midiharmony.process_midi```  
+*Extract chords, grouped chords, and unique 4‑chord quads from a MIDI file.*
+
+```midiharmony.analyze_processed_midi```  
+*Compare extracted quads against the target database and compute harmony metrics.*
+
+```midiharmony.analyze_midi```  
+*Run the full pipeline: process a MIDI file and evaluate its harmonic quality.*
+
+```midiharmony.analyze_midi_folders```  
+*Batch‑analyze all MIDI files in one or more folders and return harmony reports.*
+
+```midiharmony.helpers.get_package_data```  
+*Return a sorted list of packaged `.npz` data files with their resolved paths.*
+
+```midiharmony.helpers.get_normalized_midi_md5_hash```  
+*Compute original and normalized MD5 hashes for any MIDI file.*
+
+```midiharmony.helpers.normalize_midi_file```  
+*Normalize a MIDI file and write the normalized version to disk.*
+
+```midiharmony.helpers.is_installed```  
+*Check whether a Debian package is installed using `dpkg-query`.*
+
+```midiharmony.helpers._run_apt_get```  
+*Internal helper to run `apt-get` commands with consistent flags and timeout.*
+
+```midiharmony.helpers.install_apt_package```  
+*Idempotently install an apt package with retries, optional sudo, and optional python‑apt.*
+
+***
+
+### Project Los Angeles
+### Tegridy Code 2026

{midiharmony-26.1.27.dist-info → midiharmony-26.1.30.dist-info}/RECORD

@@ -1,10 +1,10 @@
 midiharmony/MIDI.py,sha256=kANk5j1-EMnW0cWlrKQca5A-KM7oy0BtE5eYUKPuG-k,69614
-midiharmony/README.md,sha256=-DMhg4O9Dt9l5qj67R7RIO274sC_raxh1b-CVq2ySpE,823
+midiharmony/README.md,sha256=PzIQOOQvwNK41JqEvTviD0e0EatpNPdDe_nw-ooOEL0,4686
 midiharmony/TMIDIX.py,sha256=KhSxEMs8tB0PXOHcBRbYqa63kgDBxAsvyFa9oAO2bu0,548390
 midiharmony/__init__.py,sha256=7gSewe5Li5yGW1RHy3H5fupLaL2NmXNgkpFpzSqMx2E,50
 midiharmony/helpers.py,sha256=xc6RWrNz_T2HXWJlzRDDgvKb-zexNJKpmRrAIZ9Obtc,8886
 midiharmony/midi_to_colab_audio.py,sha256=dP-YMJVrCN_orOs3iYAmlRMwlHOzme3irahnLubJohw,145302
-midiharmony/midiharmony.py,sha256=FDqsIvAVdG4iLW-GtXe45aPzyRC3_W6BLx_m-aCxBz8,16657
+midiharmony/midiharmony.py,sha256=uYthvc-DFq43Mo3HJsoD0YxLRDse5ACaMYjG5tkHhWo,20872
 midiharmony/artwork/Project-Los-Angeles.png,sha256=6SBoK-YgXOo7mluLjS_MH0KZljkhd5-9N0s3sMbax4E,989875
 midiharmony/artwork/README.md,sha256=_7QXLfyPNFWzs96MnoPecTJNWigEfSr3uWRnG6uZjk4,159
 midiharmony/artwork/Tegridy-Code-2026.png,sha256=gzDtGxeTNFvQPKzP6isxXtYIdMN7RbkTlcE6xywc_S8,594966
@@ -13,8 +13,8 @@ midiharmony/artwork/midiharmony.png,sha256=7TwKQScUh8D8-ZKEnlOO8gFSSnmXICYC3XvHN
 midiharmony/data/README.md,sha256=vpxZ5ZERJeO9HkmEI91DqtvTKnFhxfwnrVI18prYEtg,694
 midiharmony/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 midiharmony/data/all_harmonic_chords_quads.npz,sha256=-oxuq8KbyAS1CfEo-Ud1Dr6WQgAJfEMMPthaPlGRODk,37146464
-midiharmony-26.1.27.dist-info/licenses/LICENSE,sha256=Uar9eD8GksWLFWX8YWqJDo8uIstPH1at58jnS_FEDZw,11364
-midiharmony-26.1.27.dist-info/METADATA,sha256=JMWeYHqfikTr5xVX-cVRrDwD43gII9P-Py-jjwamSsA,3024
-midiharmony-26.1.27.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
-midiharmony-26.1.27.dist-info/top_level.txt,sha256=5SwvhlIS9lrTsXPh_XuuIkfxNmPMbPqOk0CVQz9eMog,12
-midiharmony-26.1.27.dist-info/RECORD,,
+midiharmony-26.1.30.dist-info/licenses/LICENSE,sha256=Uar9eD8GksWLFWX8YWqJDo8uIstPH1at58jnS_FEDZw,11364
+midiharmony-26.1.30.dist-info/METADATA,sha256=f_g76NHjkO5HIxkH5_kUx1sjiUuhXjxz5az5r-hvh3U,7062
+midiharmony-26.1.30.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
+midiharmony-26.1.30.dist-info/top_level.txt,sha256=5SwvhlIS9lrTsXPh_XuuIkfxNmPMbPqOk0CVQz9eMog,12
+midiharmony-26.1.30.dist-info/RECORD,,

midiharmony-26.1.27.dist-info/METADATA

@@ -1,72 +0,0 @@
-Metadata-Version: 2.4
-Name: midiharmony
-Version: 26.1.27
-Summary: Fast, data‑driven harmony analysis for any MIDI file
-Author-email: Alex Lev <alexlev61@proton.me>
-Maintainer-email: Alex Lev <alexlev61@proton.me>
-License-Expression: Apache-2.0
-Project-URL: Homepage, https://github.com/asigalov61/midiharmony
-Project-URL: SoundCloud, https://soundcloud.com/aleksandr-sigalov-61/
-Project-URL: Documentation, https://github.com/asigalov61/midiharmony
-Project-URL: Issues, https://github.com/asigalov61/midiharmony/issues
-Project-URL: Discussions, https://github.com/asigalov61/midiharmony/discussions
-Project-URL: Dataset, https://huggingface.co/datasets/projectlosangeles/Discover-MIDI-Dataset
-Keywords: MIDI,MIDI harmony,harmony,symbolic music,music,music harmony,harmony analysis,harmonic analysis,music information retrieval,MIR,music discovery,music search,music quality,music metadata,music recommendation,research,musicology,music analysis
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Science/Research
-Classifier: Intended Audience :: Education
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3 :: Only
-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: Topic :: Multimedia :: Sound/Audio
-Classifier: Topic :: Multimedia :: Sound/Audio :: MIDI
-Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Environment :: Console
-Classifier: Natural Language :: English
-Classifier: Typing :: Typed
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: tqdm
-Requires-Dist: matplotlib
-Requires-Dist: midirenderer
-Requires-Dist: cupy-cuda12x
-Requires-Dist: numpy==1.26.4
-Dynamic: license-file
-
-# midiharmony
-## Fast, data‑driven harmony analysis for any MIDI file
-
-<img width="1024" height="1024" alt="midiharmony" src="https://github.com/user-attachments/assets/586cf022-ce06-4cea-bfdc-ffcf9b0365d1" />
-
-***
-
-## Abstract
-
-*midiharmony provides fast, stand‑alone harmony analysis for MIDI files by comparing their chord and note relationships against a high‑quality database of extracted chord quads. This approach enables reliable detection of strong harmonic structure, musically coherent progressions, and potential inconsistencies, making it a practical tool for music‑AI pipelines, composition analysis, and large‑scale MIDI processing.*
-
-***
-
-## Install
-
-```sh
-!pip install -U midiharmony
-```
-
-***
-
-## Basic use example
-
-```python
-import midiharmony
-```
-
-### Project Los Angeles
-### Tegridy Code 2026