spacr 0.3.55__tar.gz → 0.3.60__tar.gz

{spacr-0.3.55/spacr.egg-info → spacr-0.3.60}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.55
+Version: 0.3.60
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

spacr-0.3.60/notebooks/spacr_computer_vision.ipynb

@@ -0,0 +1,150 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "335dcd14",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# use this cell to generate train and test folders: datasets/train/nc and pc and datasets/test/nc and pc\n",
+    "from spacr.io import generate_training_dataset\n",
+    "\n",
+    "settings = {'src':'path', # (path) path to source folder (where origional images were stored)\n",
+    "            'dataset_mode':'annotation', # (string) annotation, measurement, metadata\n",
+    "            'tables':['cell'],# (list of strings) The tabels present in the database, excluding png_list\n",
+    "            'test_split':0.1, # (float) Fraction of images used for the test set\n",
+    "            'annotation_column':'test', # (Optional, string) If using mode annotation, The annotation column in the database\n",
+    "            'annotated_classes':[1], # (Optional, list of integers) If using mode annotation, The interger in annotation_column, if len(annotated_classes) is 1, class 2 will be generated from a random selection of images.\n",
+    "            'metadata_type_by':'column_name', # (Optional, strin) If using mode medatada, If using mode medatada,the column class_metadata elements are in\n",
+    "            'class_metadata':[['c15'],['c19']], # (Optional, list of lists of strings) If using mode medatada, the elements that deffine each class \n",
+    "            'png_type':'cell_png', # (Optional, string) string in the path of each image (used to filter images)\n",
+    "            'nuclei_limit':False, # (Optional, bool) if cell and nucleus in tables, filter for number of nuclei per cell\n",
+    "            'pathogen_limit':0, # (Optional, integer) if cell and pathogen in tables, filter for number of pathogen per cell\n",
+    "            'uninfected':True, # (Optional, bool) if cell and pathogen in tables, bool for uninfected cells (cells)\n",
+    "            'size':None # (Optional, integer or NoneType) limit for number of images to include in total (test + train) per class\n",
+    "           }\n",
+    "\n",
+    "generate_training_dataset(settings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b4431164",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# train a torch model\n",
+    "from spacr.deep_spacr import train_test_model\n",
+    "\n",
+    "settings = {'src':'path', # (path) path to source folder (ends with datasets/training)\n",
+    "            'train':True, # (bool) - Train\n",
+    "            'test': False, # (bool) - Test\n",
+    "            'custom_model':False, # (path) - path to a custom model\n",
+    "            'classes':['nc','pc'], # (list) - list of classes (folder names in dataset/training/train or test)\n",
+    "            'model_type':'maxvit_t', # (string) - Name of torch model architecture\n",
+    "            'optimizer_type':'adamw', # (string) - type of optimizer\n",
+    "            'schedule':'reduce_lr_on_plateau', # (string) - type of scheduler (reduce_lr_on_plateau or step_lr)\n",
+    "            'loss_type':'focal_loss', # (string) - Loss function (binary_cross_entropy_with_logits or focal_loss)\n",
+    "            'normalize':True, # (bool) - Apply ImageNet normalization to images before training.\n",
+    "            'image_size':224, # (int) - Size of images, height and width.\n",
+    "            'batch_size':64, # (int) - Nr. of images per batch\n",
+    "            'epochs':10, # (int) - Nr. of epochs for training\n",
+    "            'val_split':0.1, # (float) - Fraction of images in validation dataset\n",
+    "            'learning_rate':0.0001, # (float) - Learning rate per epoch\n",
+    "            'weight_decay':0.00001, # (float) - Fraction of random weights decay (regularization)\n",
+    "            'dropout_rate':0.1, # (float) - Fraction of weights to omit per epoch (regularization)\n",
+    "            'init_weights':True, # (bool) - Initiate model with ImageNet weights\n",
+    "            'amsgrad':True, # (bool) - guard against exploding gradients\n",
+    "            'use_checkpoint':True, # (bool) - checkpoint gradient calculations to save VRAM at the expence of computation\n",
+    "            'gradient_accumulation':True, # (bool) - Accumulate gradients to mimic larger batches\n",
+    "            'gradient_accumulation_steps':4, # (int) - Epochs to accumulate gradients\n",
+    "            'intermedeate_save':True, # Save intermediate states of the model\n",
+    "            'pin_memory':True, # (bool) - Whether to pin memory for the data loader\n",
+    "            'n_jobs':30, # (int) - Number of threads to use\n",
+    "            'train_channels':['r','g','b'], # (list of 'r', 'g', and/or 'b') - PNG channels to use for training\n",
+    "            'augment':False, # (bool) - Augment the dataset, vertical, horizontal flip and rotate each image to artificially expand the dataset 8 fold.\n",
+    "            'verbose':True}\n",
+    "\n",
+    "train_test_model(settings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5770fb79",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# generate a tar dataset\n",
+    "\n",
+    "from spacr.io import generate_dataset\n",
+    "\n",
+    "settings = {'src':'path', # (path) path to source folder (where origional images were stored)\n",
+    "           'file_metadata':'cell_png', # (Optional, string) string in the path of each image (used to filter images)\n",
+    "           'experiment':'test', # (string) - Name of dataset\n",
+    "           'sample':10000} # (Optional, integer or NoneType) limit for number of images to include in the dataset\n",
+    "\n",
+    "generate_dataset(settings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "086fcefb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# apply a model to a tar dataset\n",
+    "\n",
+    "from spacr.deep_spacr import apply_model_to_tar\n",
+    "\n",
+    "settings = {'dataset':'path.tar', # (path) - path to tar dataset (ends with .tar) \n",
+    "            'model_path':'path.pth', # (path) - path to model (ends with .pth) \n",
+    "            'file_type':'cell_png', # (Optional, string) string in the path of each image (used to filter images)\n",
+    "            'image_size':224, # (int) - Size of images, height and width\n",
+    "            'batch_size':64, # (int) - Nr. of images per batch\n",
+    "            'normalize':True, # (bool) - Apply ImageNet normalization to images before training.\n",
+    "            'score_threshold':0.5, # (float) - Score to byass the classes\n",
+    "            'n_jobs':30, # (int) - Number of threads to use\n",
+    "            'verbose':True}\n",
+    "\n",
+    "result_df = apply_model_to_tar(settings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "28debecd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "spacr",
+   "language": "python",
+   "name": "spacr"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

{spacr-0.3.55 → spacr-0.3.60}/setup.py

@@ -69,7 +69,7 @@ dependencies = [
 
 setup(
     name="spacr",
-    version="0.3.55",
+    version="0.3.60",
     author="Einar Birnir Olafsson",
     author_email="olafsson@med.umich.com",
     description="Spatial phenotype analysis of crisp screens (SpaCr)",

{spacr-0.3.55 → spacr-0.3.60}/spacr/ml.py

@@ -191,18 +191,18 @@ def prepare_formula(dependent_variable, random_row_column_effects=False):
     if random_row_column_effects:
         # Random effects for row and column + gene weighted by gene_fraction + grna weighted by fraction
         return f'{dependent_variable} ~ fraction:grna + gene_fraction:gene'
-    return f'{dependent_variable} ~ fraction:grna + gene_fraction:gene + row + column'
+    return f'{dependent_variable} ~ fraction:grna + gene_fraction:gene + row_name + column_name'
 
 def fit_mixed_model(df, formula, dst):
     from .plot import plot_histogram
 
-    """Fit the mixed model with plate, row, and column as random effects and return results."""
+    """Fit the mixed model with plate, row_name, and column_name as random effects and return results."""
     # Specify random effects for plate, row, and column
     model = smf.mixedlm(formula, 
                         data=df, 
                         groups=df['plate'], 
-                        re_formula="1 + row + column", 
-                        vc_formula={"row": "0 + row", "column": "0 + column"})
+                        re_formula="1 + row_name + column_name", 
+                        vc_formula={"row_name": "0 + row_name", "column_name": "0 + column_name"})
     
     mixed_model = model.fit()
 
@@ -284,7 +284,7 @@ def check_and_clean_data(df, dependent_variable):
     df = handle_missing_values(df, ['fraction', dependent_variable])
     
     # Step 2: Ensure grna, gene, plate, row, column, and prc are categorical types
-    df = ensure_valid_types(df, ['grna', 'gene', 'plate', 'row_name', 'column', 'prc'])
+    df = ensure_valid_types(df, ['grna', 'gene', 'plate', 'row_name', 'column_name', 'prc'])
     
     # Step 3: Check for multicollinearity in fraction and the dependent variable
     df_cleaned = check_collinearity(df, ['fraction', dependent_variable])
@@ -295,7 +295,7 @@ def check_and_clean_data(df, dependent_variable):
     df_cleaned['prc'] = df['prc']
     df_cleaned['plate'] = df['plate']
     df_cleaned['row_name'] = df['row_name']
-    df_cleaned['column'] = df['column']
+    df_cleaned['column_name'] = df['column']
 
     # Create a new column 'gene_fraction' that sums the fractions by gene within the same well
     df_cleaned['gene_fraction'] = df_cleaned.groupby(['prc', 'gene'])['fraction'].transform('sum')
@@ -631,9 +631,9 @@ def regression(df, csv_path, dependent_variable='predictions', regression_type=N
                random_row_column_effects=False, nc='233460', pc='220950', controls=[''],
                dst=None, cov_type=None, plot=False):
     
-    from spacr.plot import volcano_plot, plot_histogram
-    from spacr.ml import create_volcano_filename, check_and_clean_data, prepare_formula, scale_variables
-    
+    from .plot import volcano_plot, plot_histogram
+    #from .ml import create_volcano_filename, check_and_clean_data, prepare_formula, scale_variables
+        
     # Generate the volcano filename
     volcano_path = create_volcano_filename(csv_path, regression_type, alpha, dst)
 
@@ -1085,7 +1085,12 @@ def process_scores(df, dependent_variable, plate, min_cell_count=25, agg_type='m
     if 'plate_name' in df.columns:
         df.drop(columns=['plate'], inplace=True)
         df = df.rename(columns={'plate_name': 'plate'})
-    
+        
+    if 'row' in df.columns:
+        df = df.rename(columns={'row': 'row_name'})
+    if 'col' in df.columns:
+        df = df.rename(columns={'row': 'column_name'})
+        
     if plate is not None:
         df['plate'] = plate
 

{spacr-0.3.55 → spacr-0.3.60/spacr.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.55
+Version: 0.3.60
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

{spacr-0.3.55 → spacr-0.3.60}/spacr.egg-info/SOURCES.txt

@@ -86,11 +86,12 @@ docs/source/_build/html/_static/js/html5shiv-printshiv.min.js
 docs/source/_build/html/_static/js/html5shiv.min.js
 docs/source/_build/html/_static/js/theme.js
 fonts/OpenSans-Regular.ttf
-notebooks/cv_scoring_nb.ipynb
-notebooks/deep_learning_spacr.ipynb
-notebooks/machine_learning_spacr_nb.ipynb
-notebooks/spacr_0.1_all_settings_git.ipynb
-notebooks/spacr_0.1_minimal.ipynb
+notebooks/spacr_computer_vision.ipynb
+notebooks/old/cv_scoring_nb.ipynb
+notebooks/old/deep_learning_spacr.ipynb
+notebooks/old/machine_learning_spacr_nb.ipynb
+notebooks/old/spacr_0.1_all_settings_git.ipynb
+notebooks/old/spacr_0.1_minimal.ipynb
 path/home/carruthers/datasets/plate1/measurements/measurements.db
 path/home/carruthers/datasets/plate1/settings/measure_crop_settings.csv
 path/settings/preprocess_generate_masks_settings.csv