:twisted_rightwards_arrows: Merge branch 'develop'

.env_sample

@@ -0,0 +1 @@
+HF_TOKEN=hf_YOUR_AWESOME_TOKEN

.gitignore

@@ -1,3 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# c++ generated files
+*.out
+*.exe
+
+# my custom gitignores
 lightning_logs/
 *.pth
-my-awesome-model/
+my-awesome-model/
+my-awesome-model-200/
+my-awesome-model-4000/

app.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import random
 from typing import Any
 
@@ -6,15 +7,19 @@ import numpy as np
 import pandas as pd
 from pytorch_lightning import Trainer, LightningModule, LightningDataModule
 from pytorch_lightning.utilities.types import OptimizerLRScheduler, STEP_OUTPUT, EVAL_DATALOADERS, TRAIN_DATALOADERS
+from torch.nn.utils.rnn import pad_sequence
 from torch.utils.data import DataLoader, Dataset
 from torchmetrics.classification import BinaryAccuracy, BinaryAUROC, BinaryF1Score, BinaryPrecision, BinaryRecall
 from transformers import BertModel, BatchEncoding, BertTokenizer, TrainingArguments
 from transformers.modeling_outputs import BaseModelOutputWithPoolingAndCrossAttentions
 import torch
 from torch import nn
-from datasets import load_dataset
+from datasets import load_dataset, IterableDataset
 from huggingface_hub import PyTorchModelHubMixin
 
+from dotenv import load_dotenv
+from huggingface_hub import login
+
 timber = logging.getLogger()
 # logging.basicConfig(level=logging.DEBUG)
 logging.basicConfig(level=logging.INFO)  # change to level=logging.DEBUG to print more logs...
@@ -34,6 +39,30 @@ BACKWARD = "BACKWARD_INPUT"
 DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 
+def login_inside_huggingface_virtualmachine():
+  # Load the .env file, but don't crash if it's not found (e.g., in Hugging Face Space)
+  try:
+    load_dotenv()  # Only useful on your laptop if .env exists
+    print(".env file loaded successfully.")
+  except Exception as e:
+    print(f"Warning: Could not load .env file. Exception: {e}")
+
+  # Try to get the token from environment variables
+  try:
+    token = os.getenv("HF_TOKEN")
+
+    if not token:
+      raise ValueError("HF_TOKEN not found. Make sure to set it in the environment variables or .env file.")
+
+    # Log in to Hugging Face Hub
+    login(token)
+    print("Logged in to Hugging Face Hub successfully.")
+
+  except Exception as e:
+    print(f"Error during Hugging Face login: {e}")
+    # Handle the error appropriately (e.g., exit or retry)
+
+
 def one_hot_e(dna_seq: str) -> np.ndarray:
   mydict = {'A': np.asarray([1.0, 0.0, 0.0, 0.0]), 'C': np.asarray([0.0, 1.0, 0.0, 0.0]),
             'G': np.asarray([0.0, 0.0, 1.0, 0.0]), 'T': np.asarray([0.0, 0.0, 0.0, 1.0]),
@@ -136,19 +165,25 @@ def insert_debug_motif_at_random_position(seq, DEBUG_MOTIF):
   return output
 
 
-class MQTLDataset(Dataset):
-  def __init__(self, dataset, check_if_pipeline_is_ok_by_inserting_debug_motif=False):
-    self.dataset = dataset
+class MQTLDataset(IterableDataset):
+  def __init__(self, m_dataset, seq_len, check_if_pipeline_is_ok_by_inserting_debug_motif=False):
+    self.dataset = m_dataset
     self.check_if_pipeline_is_ok_by_inserting_debug_motif = check_if_pipeline_is_ok_by_inserting_debug_motif
     self.debug_motif = "ATCGCCTA"
+    self.seq_len = seq_len
     pass
 
-  def __len__(self):
-    return len(self.dataset)
-
-  def __getitem__(self, idx):
-    seq = self.dataset[idx]['sequence']  # Fetch the 'sequence' column
-    label = self.dataset[idx]['label']  # Fetch the 'label' column (or whatever target you use)
+  def __iter__(self):
+    for row in self.dataset:
+      processed = self.preprocess(row)
+      if processed is not None:
+        yield processed
+
+  def preprocess(self, row):
+    seq = row['sequence']  # Fetch the 'sequence' column
+    if len(seq) != self.seq_len:
+      return None  # skip problematic row!
+    label = row['label']  # Fetch the 'label' column (or whatever target you use)
     if label == 1 and self.check_if_pipeline_is_ok_by_inserting_debug_motif:
       seq = insert_debug_motif_at_random_position(seq=seq, DEBUG_MOTIF=self.debug_motif)
     seq_rc = reverse_complement_dna_seq(seq)
@@ -162,16 +197,36 @@ class MQTLDataset(Dataset):
     return [ohe_seq, ohe_seq_rc], label_np_array
 
 
+# def collate_fn(batch):
+#   sequences, labels = zip(*batch)
+#   ohe_seq, ohe_seq_rc = sequences[0], sequences[1]
+#   # Pad sequences to the maximum length in this batch
+#   padded_sequences = pad_sequence(ohe_seq, batch_first=True, padding_value=0)
+#   padded_sequences_rc = pad_sequence(ohe_seq_rc, batch_first=True, padding_value=0)
+#   # Convert labels to a tensor
+#   labels = torch.stack(labels)
+#   return [padded_sequences, padded_sequences_rc], labels
+
+
 class MqtlDataModule(LightningDataModule):
   def __init__(self, train_ds: Dataset, val_ds: Dataset, test_ds: Dataset, batch_size=16):
     super().__init__()
     self.batch_size = batch_size
-    self.train_loader = DataLoader(train_ds, batch_size=self.batch_size, shuffle=True, num_workers=15,
-                                   persistent_workers=True)
-    self.validate_loader = DataLoader(val_ds, batch_size=self.batch_size, shuffle=False, num_workers=15,
-                                      persistent_workers=True)
-    self.test_loader = DataLoader(test_ds, batch_size=self.batch_size, shuffle=False, num_workers=15,
-                                  persistent_workers=True)
+    self.train_loader = DataLoader(train_ds, batch_size=self.batch_size, shuffle=False,
+                                   # collate_fn=collate_fn,
+                                   num_workers=15,
+                                   # persistent_workers=True
+                                   )
+    self.validate_loader = DataLoader(val_ds, batch_size=self.batch_size, shuffle=False,
+                                      # collate_fn=collate_fn,
+                                      num_workers=15,
+                                      # persistent_workers=True
+                                      )
+    self.test_loader = DataLoader(test_ds, batch_size=self.batch_size, shuffle=False,
+                                  # collate_fn=collate_fn,
+                                  num_workers=15,
+                                  # persistent_workers=True
+                                  )
     pass
 
   def prepare_data(self):
@@ -376,17 +431,40 @@ def start(classifier_model, model_save_path, is_attention_model=False, m_optimiz
   if is_binned:
     file_suffix = "_binned"
 
-  dataset_map = load_dataset("fahimfarhan/mqtl-classification-dataset-binned-200")
-
-  train_dataset = MQTLDataset(dataset_map["train"], check_if_pipeline_is_ok_by_inserting_debug_motif=is_debug)
-  val_dataset = MQTLDataset(dataset_map["validate"], check_if_pipeline_is_ok_by_inserting_debug_motif=is_debug)
-  test_dataset = MQTLDataset(dataset_map["test"], check_if_pipeline_is_ok_by_inserting_debug_motif=is_debug)
+  data_files = {
+    # small samples
+    "train_binned_200": "/home/soumic/Codes/mqtl-classification/src/inputdata/dataset_200_train_binned.csv",
+    "validate_binned_200": "/home/soumic/Codes/mqtl-classification/src/inputdata/dataset_200_validate_binned.csv",
+    "test_binned_200": "/home/soumic/Codes/mqtl-classification/src/inputdata/dataset_200_test_binned.csv",
+    # large samples
+    "train_binned_4000": "/home/soumic/Codes/mqtl-classification/src/inputdata/dataset_4000_train_binned.csv",
+    "validate_binned_4000": "/home/soumic/Codes/mqtl-classification/src/inputdata/dataset_4000_validate_binned.csv",
+    "test_binned_4000": "/home/soumic/Codes/mqtl-classification/src/inputdata/dataset_4000_test_binned.csv",
+  }
+
+  dataset_map = None
+  is_my_laptop = os.path.isfile("/home/soumic/Codes/mqtl-classification/src/inputdata/dataset_4000_test_binned.csv")
+  if is_my_laptop:
+    dataset_map = load_dataset("csv", data_files=data_files, streaming=True)
+  else:
+    dataset_map = load_dataset("fahimfarhan/mqtl-classification-datasets", streaming=True)
+
+  train_dataset = MQTLDataset(dataset_map[f"train_binned_{WINDOW}"],
+                              check_if_pipeline_is_ok_by_inserting_debug_motif=is_debug,
+                              seq_len=WINDOW
+                              )
+  val_dataset = MQTLDataset(dataset_map[f"validate_binned_{WINDOW}"],
+                            check_if_pipeline_is_ok_by_inserting_debug_motif=is_debug,
+                            seq_len=WINDOW)
+  test_dataset = MQTLDataset(dataset_map[f"test_binned_{WINDOW}"],
+                             check_if_pipeline_is_ok_by_inserting_debug_motif=is_debug,
+                             seq_len=WINDOW)
 
   data_module = MqtlDataModule(train_ds=train_dataset, val_ds=val_dataset, test_ds=test_dataset)
 
   classifier_model = classifier_model  #.to(DEVICE)
   try:
-    classifier_model = classifier_model.from_pretrained("my-awesome-model")
+    classifier_model = classifier_model.from_pretrained(f"my-awesome-model-{WINDOW}")
   except Exception as x:
     print(x)
 
@@ -406,13 +484,18 @@ def start(classifier_model, model_save_path, is_attention_model=False, m_optimiz
   torch.save(classifier_module.state_dict(), model_save_path)
 
   #  save locally
-  classifier_model.save_pretrained("my-awesome-model")
+  model_subdirectory = f"my-awesome-model-{WINDOW}"
+  classifier_model.save_pretrained(model_subdirectory)
 
   # push to the hub
-  classifier_model.push_to_hub(repo_id="fahimfarhan/mqtl-classifier-model", commit_message=":tada: Push model using huggingface_hub")
+  classifier_model.push_to_hub(
+    repo_id="fahimfarhan/mqtl-classifier-model",
+    # subfolder=f"my-awesome-model-{WINDOW}", subfolder didn't work :/
+    commit_message=f":tada: Push model for window size {WINDOW}"
+  )
 
   # reload
-  model = classifier_model.from_pretrained("my-awesome-model")
+  model = classifier_model.from_pretrained(f"my-awesome-model-{WINDOW}")
   # repo_url = "https://huggingface.co/fahimfarhan/mqtl-classifier-model"
   #
   # push_to_hub(
@@ -429,18 +512,23 @@ def start(classifier_model, model_save_path, is_attention_model=False, m_optimiz
 
 
 if __name__ == '__main__':
+  login_inside_huggingface_virtualmachine()
+
   WINDOW = 200
   simple_cnn = Cnn1dClassifier(seq_len=WINDOW)
   simple_cnn.enable_logging = True
 
   start(classifier_model=simple_cnn, model_save_path=simple_cnn.file_name, WINDOW=WINDOW,
-        dataset_folder_prefix="inputdata/", is_debug=True, max_epochs=3)
+        dataset_folder_prefix="inputdata/", is_debug=True, max_epochs=10)
 
   pass
 
-
 """
 lightning_logs/
 *.pth
 my-awesome-model
-"""
+
+INFO:root:validate_acc = 0.5625, validate_auc = 0.5490195751190186, validate_f1_score = 0.30000001192092896, validate_precision = 0.6000000238418579, validate_recall = 0.20000000298023224
+/home/soumic/Codes/mqtl-classification/venv/lib/python3.10/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:424: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=15` in the `DataLoader` to improve performance.
+
+"""

requirements.txt

@@ -29,4 +29,5 @@ torchviz
 gReLU # luckily now available in pip!
 # gReLU @ git+https://github.com/Genentech/gReLU # @623fee8023aabcef89f0afeedbeafff4b71453af
 # lightning[extra]  # cz I got a stupid warning in the console logs
-torchmetrics
+torchmetrics
+python-dotenv