Merge Develop Into Master

.gitignore

@@ -105,3 +105,5 @@ ENV/
 # IDE settings
 .vscode/
 .idea/
+
+.DS_Store

docs/pc_mouseparty.md

@@ -1,4 +1,58 @@
- 
+
 # pc_mouseparty module
 
-::: pc_mouseparty.pc_mouseparty
+::: pc_mouseparty.pc_mouseparty
+
+:::pc_mouseparty.pc_mouseparty.vid_behavior.boris_extraction
+
+function: threshold_bouts(start_stop_array, min_iti, min_bout):
+    """
+    thresholds behavior bouts
+    by combining behavior bouts with interbout intervals of < min_iti
+    and then removing remaining bouts of < min_bout
+
+    Args (3 total):
+        start_stop_array: numpy array of dim (# of bouts, 2)
+        min_iti: float, min interbout interval in seconds
+        min_bout: float, min bout length in seconds
+
+    Returns (1):
+        start_stop_array: numpy array (ndim=(n bouts, 2))
+            of start&stop times (ms)
+    """
+
+function get_behavior_bouts(boris_df, subject, behavior, min_iti=0, min_bout=0):
+    """
+    extracts behavior bout start and stop times from a boris df
+    thresholds individually by subject and behavior
+    returns start_stop_array ordered by start values
+
+    Args (5 total, 3 required):
+        boris_df: pandas dataframe of a boris file (aggregated event table)
+        subject: list of strings, desired subject(s) (as written in boris_df)
+        behavior: list of strings, desired behavior(s) (as written in boris_df)
+        min_iti: float, default=0, bouts w/ itis(s) < min_iti will be combined
+        min_bout: float, default=0, bouts < min_bout(s) will be deleted
+
+    Returns (1):
+        numpy array (ndim=(n bouts, 2)) of start&stop times (ms)
+
+function save_behavior_bouts(directory, boris_df, subject, behavior, min_bout=0,
+                        min_iti=0, filename=None):
+    """
+    saves a numpy array of start&stop times (ms)
+    as filename: subject_behavior_bouts.npy
+
+    Args (7 total, 4 required):
+        directory: path to folder where filename.npy will be saved
+            path format: './folder/folder/'
+        boris_df: pandas dataframe of a boris file (aggregated event table)
+        subject: list of strings, desired subjects (as written in boris_df)
+        behavior: list of strings, desired behaviors (as written in boris_df)
+        min_iti: float, default=0, bouts w/ itis(s) < min_iti will be combined
+        min_bout: float, default=0, bouts < min_bouts(s) will be deleted
+        filename: string, default=None, must end in .npy
+
+    Returns:
+        none
+    """

mkdocs.yml

@@ -82,5 +82,4 @@ nav:
     - Examples:
         - examples/intro.ipynb
     - API Reference:
-          - pc_mouseparty module: pc_mouseparty.md
           - test_functions module: test_functions.md

pc_mouseparty/medpc/medpc_extraction.py

@@ -0,0 +1,93 @@
+import re
+import pandas as pd
+
+
+def medpc_txt2df(text_file_path):
+    """
+    This function reads a medpc text data file into a pandas dataframe.
+
+    Args (1 total, 1 required):
+        text_file_path : str, a path to a medpc text file as a string.
+
+    Return (1):
+        df : pandas dataframe, a dataframe with the medpc data.
+    """
+    # Open the medpc text file
+    # with open(text_file_path, "r") as file: # use this for package
+    with open(text_file_path.name) as file:  # use this for gradio app
+        medpc_txt_file = file.read()
+
+    # split the file with each new line an element in a list
+    medpc_txt_file_lst = medpc_txt_file.split('\n')
+
+    # remove all empty elements in the list
+    medpc_txt_file_lst = list(filter(None, medpc_txt_file_lst))
+
+    # add medpc output vectors to lists
+    result = []
+    temp = []
+    for item in medpc_txt_file_lst:
+        # add values taht comeafter ":" to a list as floats
+        if re.search(r'^\s*\d+:\s+', item):
+            temp.append(item)
+        else:
+            if temp:
+                floats = [float(x) for x in re.findall(r'\d+\.\d+',
+                                                       ''.join(temp))]
+                result.append(floats)
+                temp = []
+            result.append(item)
+    if temp:
+        floats = [float(x) for x in re.findall(r'\d+\.\d+',
+                                               ''.join(temp))]
+        result.append(floats)
+
+    # convert the list of lists and strings to
+    # a dictionary with everything before ":"
+    # as a key and everything after as the value
+    result_dict = {}
+    for item in result:
+        if ':' in item:
+            index = item.index(':')
+            key = item[:index]
+            value = item[index+1:].strip()
+            if not value:
+                value = result[result.index(item)+1]
+            result_dict[key] = value
+        elif type(item) == str:
+            result_dict[item] = []
+
+    # convert the dictionary to a dataframe
+    # values are of unequal length
+    # convert all values to lists
+    pd_series_lst = []
+    for i, j in result_dict.items():
+        if type(j) != list:
+            result_dict[i] = [j]
+        else:
+            result_dict[i] = j
+        pd_series_lst.append(pd.Series(j))
+
+    # add list to dataframe
+    df = pd.concat(pd_series_lst, axis=1)
+    df.columns = result_dict.keys()
+
+    return (df)
+
+
+def cut_zeros(df):
+    """
+    This function removes all trailing zeros of the medpc dataframe.
+
+    Args (2 total, 1 required):
+        df: pandas dataframe, a dataframe with the medpc data.
+
+    Return (1):
+        df : pandas dataframe, a dataframe with the medpc data
+        with trailing zeros removed.
+    """
+    # find index of last row that does not only ahve 0 and Nan
+    last_idx = df[df.sum(axis=1).ne(0)].index[-1]
+    df = df[:last_idx+1]
+
+    return (df)