morphgen-rates 0.4.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

morphgen_rates/data.py

@@ -22,85 +22,82 @@ def _local_data_path(filename='morph_data', ext="csv"):
   return work_dir / f"{filename}.{ext}"
 
 
-def get_data(key):
+def get_data(area, neuron_type):
   """
-  Retrieve a dataset entry using a key-path of the form
-  "<brain region>/<neuron class>/<subcellular section>".
+  Retrieve summary morphology statistics for a given brain area and neuron class.
 
-  The argument `data_path` is interpreted as a slash-separated path of keys used
-  to traverse a nested dataset dictionary. The selected dataset is expected to
-  contain both Sholl-plot statistics and bifurcation statistics; when both are
-  available, this function returns a standardized dictionary compatible with
-  `compute_rates`.
+  This function loads a local CSV dataset, filters rows matching the requested
+  `area` and `neuron_type`, and aggregates statistics by `section_type`. The
+  output is a nested dictionary keyed by section type (e.g., soma, apical, basal),
+  containing:
+
+  - Summary statistics for bifurcation counts and total length
+  - Estimated number of primary neurites at the soma (Count0)
+  - Sholl plot summary statistics (bin size, mean counts, standard deviation)
 
   Parameters
   ----------
-  key : str
-      Dataset identifier expressed as a key path:
-
-      "<brain region>/<neuron class>/<subcellular section>"
-
-      Examples:
-      - "CTX/pyr/apical"
-      - "HPC/pyr/basal"
-
-      Each component is used as a successive key lookup into the nested dataset
-      container.
+  area : str
+      Brain region identifier used in the dataset (must match values in the
+      'area' column of the CSV)
+  neuron_type : str
+      Neuron class identifier used in the dataset (must match values in the
+      'neuron_type' column of the CSV)
 
   Returns
   -------
   dict
-      If both Sholl and bifurcation information are present for the selected dataset,
-      returns:
+      Nested dictionary structured as:
 
       data = {
-        "sholl": {
-          "bin_size": float,
-          "mean": numpy.ndarray,   # shape (K,)
-          "var":  numpy.ndarray,   # shape (K,)
-        },
-        "bifurcations": {
-          "mean": float,
-          "var":  float,
+        "<section_type>": {
+          "bifurcation_count": {"mean": ..., "std": ..., "min": ..., "max": ...},
+          "total_length": {"mean": ..., "std": ..., "min": ..., "max": ...},
+          "primary_count": {"mean": ..., "std": ..., "min": ..., "max": ...},
+          "sholl_plot": {
+            "bin_size": float,
+            "mean": list[float],
+            "std": list[float],
+          },
         },
+        ...
       }
 
-      Where:
-      - `data["sholl"]["bin_size"]` is the spatial bin size used to define Sholl shells
-      - `data["sholl"]["mean"]` is the mean Sholl intersection count per radial bin
-      - `data["sholl"]["var"]` is the variance of the Sholl intersection count per bin
-      - `data["bifurcations"]["mean"]` is the mean bifurcation count
-      - `data["bifurcations"]["var"]` is the variance of the bifurcation count
+      Notes on fields:
+      - `primary_count` corresponds to the row group labeled 'Count0'
+      - Sholl values are collected from rows whose metric name starts with 'Count'
+        (including 'Count0'); users may want to interpret/plot them as a function
+        of radial bin index multiplied by `bin_size`
 
   Raises
   ------
-  KeyError
-      If any key along `data_path` is missing (brain region, neuron class, or section)
-  ValueError
-      If the selected dataset does not contain both Sholl and bifurcation data, or
-      if the provided arrays have incompatible shapes
+  AssertionError
+      If no rows match the requested `area` and `neuron_type`
 
   Notes
   -----
-  - `data_path` is a *key path*, not a filesystem path
-  - The function assumes the dataset entry referenced by `data_path` includes:
-      - Sholl bin size, mean array, variance array
-      - Bifurcation mean and variance
+  - The function expects the local CSV to include at least the following columns:
+      'area', 'neuron_type', 'neuron_name', 'section_type', 'bin_size'
+      plus metric columns including:
+        - 'bifurcation_count'
+        - 'total_length'
+        - 'Count0', 'Count1', ... (Sholl counts per radial bin)
+  - Statistics are computed using `pandas.DataFrame.groupby(...).describe()`.
+    Only the summary columns 'mean', 'std', 'min', 'max' are retained.
 
   Examples
   --------
-  >>> data = get("CTX/pyr/apical")
-  >>> data["sholl"]["bin_size"]
+  >>> data = get_data("CTX", "pyr")
+  >>> data["apical"]["bifurcation_count"]["mean"]
+  42.0
+  >>> data["apical"]["sholl_plot"]["bin_size"]
   50.0
-  >>> data["bifurcations"]["mean"]
-  12.3
+  >>> len(data["apical"]["sholl_plot"]["mean"])
+  20
   """
+  
   data = {}
 
-  # split the key
-  parts = tuple(p.strip() for p in key.split("/") if p.strip())
-  if len(parts) != 2:
-      raise ValueError(f"Expected key like 'area/neuron_type', got: {key!r}")
   area, neuron_type = parts
     
   # load data
@@ -108,6 +105,9 @@ def get_data(key):
 
   # select specific area and neuron type
   df = df[(df['area'] == area) & (df['neuron_type'] == neuron_type)]
+
+  # ensure that there are area and neuron_type in the df
+  assert df.shape[0] > 0, "The area {area} or neuron class {neuron_type} are not known"
   
   # neuron name unnecessary
   df.drop(['area', 'neuron_type', 'neuron_name'], axis=1, inplace=True)
@@ -122,8 +122,6 @@ def get_data(key):
   for section_type, row in df.iterrows():
     data[section_type] = {}
 
-    print()
-
     # get statistics
     for data_type in ['bifurcation_count', 'total_length']:
       tmp = row.loc[row.index.get_level_values(0) == data_type, :]

{morphgen_rates-0.4.0.dist-info → morphgen_rates-0.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: morphgen-rates
-Version: 0.4.0
+Version: 0.5.0
 Summary: Compute bifurcation and annihilation rates from morphology data
 Author-email: Francesco Cavarretta <fcavarretta@ualr.edu>
 Requires-Python: >=3.9

morphgen_rates-0.5.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+morphgen_rates/__init__.py,sha256=UE8YWsulDIfeYhGb5GHdkakUIFx4j9H3ZkoKoaDCd_0,179
+morphgen_rates/data.py,sha256=Onc2dRlB_QXpgScDzHCE7DRtg6PLtFld5W91QGuDkYo,4518
+morphgen_rates/init_count.py,sha256=PhYlp0-CzRdf8opTKb-om3cFIKSv5M8eTcyKy1_IFMI,7283
+morphgen_rates/rates.py,sha256=2Gn3Ew2uVJ7c_LdYJogxS-jAM9q-039y0maWi4CNpTM,6442
+morphgen_rates-0.5.0.dist-info/licenses/LICENSE,sha256=VONsnKVXQRcWwCaHWHuwMtemIj9jNJSmpunazxlyvOk,670
+morphgen_rates-0.5.0.dist-info/METADATA,sha256=xYYNva-7mn6Vk-iFKKJJUg3jw_phgW-iZvHeSd4z7gk,1178
+morphgen_rates-0.5.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+morphgen_rates-0.5.0.dist-info/top_level.txt,sha256=UYPGC2dGp9xD_4iVxVVTkKaizBA4XeDNM7OBC_DCWRk,15
+morphgen_rates-0.5.0.dist-info/RECORD,,

morphgen_rates-0.4.0.dist-info/RECORD

@@ -1,9 +0,0 @@
-morphgen_rates/__init__.py,sha256=UE8YWsulDIfeYhGb5GHdkakUIFx4j9H3ZkoKoaDCd_0,179
-morphgen_rates/data.py,sha256=yj_GT3ks6ukwtALfC4Bklcwu3MeTOr-2BGGo5W0ZxM0,4330
-morphgen_rates/init_count.py,sha256=PhYlp0-CzRdf8opTKb-om3cFIKSv5M8eTcyKy1_IFMI,7283
-morphgen_rates/rates.py,sha256=2Gn3Ew2uVJ7c_LdYJogxS-jAM9q-039y0maWi4CNpTM,6442
-morphgen_rates-0.4.0.dist-info/licenses/LICENSE,sha256=VONsnKVXQRcWwCaHWHuwMtemIj9jNJSmpunazxlyvOk,670
-morphgen_rates-0.4.0.dist-info/METADATA,sha256=Xb088-i11lgv8rY4jVvQ3ghYDpyliSw83yjC-kfYANw,1178
-morphgen_rates-0.4.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-morphgen_rates-0.4.0.dist-info/top_level.txt,sha256=UYPGC2dGp9xD_4iVxVVTkKaizBA4XeDNM7OBC_DCWRk,15
-morphgen_rates-0.4.0.dist-info/RECORD,,