Merge branch 'csv_tools' into 'master'

csv tools in dedicated file

See merge request !8

benb.py

@@ -27,68 +27,6 @@ def rand_web_color_hex():
     return "#{}".format(rgb)
 
 
-def fix_bt(code_in, as_mnp=False):
-    """
-    Parser for Beheertype codes to repair abbreviated codes and/or MNP extension
-    eg. 02.01     --> N02.01 if as_mnp==False
-        02.01     --> N01.01.00 if as_mnp==True
-        N05.01    --> N05.01  if as_mnp==False
-        N05.01    --> N05.01.00  if as_mnp==True
-        N04.02.01 --> N04.02.01 if as_mnp==False
-        N04.02.01 --> N04.02.01 if as_mnp==True
-    BT Code is as follows <N><AA>.<BB>.<CC>
-    N = letter, may be missing
-    A = two digits indicating top level beheertype "TOP"
-    B = two digits indicating sub level beheertype "SUB"
-    C = two digits indicating neergeschaald beheertype if > 00. Else "00" as used in MNP param notation  "NEER"
-    N04.02.00 is equivalent to N04.02
-    :param code_in: beheertypecode in any format
-    :param as_mnp: return MNP style beheertypecode, default=False
-    :return: beheertypecode
-    """
-    if isinstance(code_in, numbers.Number):
-        code_in = str(code_in)
-
-    # Identify parts of code
-    parts = code_in.split(".")
-    if len(parts) == 1:
-        raise Exception("Unexpected BT code: {}".format(code_in))
-    elif len(parts) == 2:
-        top, sub = parts
-        neer = None
-    elif len(parts) == 3:
-        top, sub, neer = parts
-
-    # Verify TOP and add "N" is required
-    if top.isdigit():
-        top = "N{0}".format(top.zfill(2))
-    else:
-        assert top[0].isupper(), "Unexpected BT Code format: {}".format(code_in)
-
-    # Verify SUB
-    assert sub.isdigit and len(sub) == 2, "Unexpected BT Code format: {}".format(
-        code_in
-    )
-
-    # Verify NEER and check if it is neergeschaald or not
-    keep_neer = False
-    if neer:
-        assert neer.isdigit and len(neer) == 2, "Unexpected BT Code format: {}".format(
-            code_in
-        )
-        if int(neer) > 0:
-            keep_neer = True
-
-    # Construct output
-    head = "{}.{}".format(top, sub)
-    if keep_neer:
-        return "{}.{}".format(head, neer)
-    elif as_mnp:
-        return "{}.00".format(head)
-    else:
-        return head
-
-
 def pnt2square_id(east_north, size, of="full"):
     """
     Used to slot a point into a geographical square based on its coordinates.
@@ -129,21 +67,6 @@ def pnt2square_id(east_north, size, of="full"):
         raise
 
 
-def draagkracht_ww(frequentie, trouw, th):
-    """
-    Draagkracht formule volgens Wieger Wamelink. Zie MS Teams discussie 16-07-2020 MNP2020/Fase 7 Objectivering Draagk..
-    :param frequentie: gemiddelde frequentie van soort X binnen beheertype Y
-    :param trouw: gemiddelde trouw van soort X binnen beheertype Y
-    :param th: minumum draagkracht value
-    :return: draagkracht soort X - beheertype Y combinatie, gemaximaliseerd tot 1.
-    """
-    dk = np.min([np.multiply(np.divide(np.max([frequentie, trouw]), 100), 5), 1])
-    if dk >= th:
-        return dk
-    else:
-        return np.nan
-
-
 def gen_squares(x_ul, y_ul, nrow, ncol, size):
     """
     Generate geodataframe with square polygons
@@ -225,64 +148,6 @@ def colrow2xy(colrow, rio_object=None, affine_in=None):
     return x, y
 
 
-def csv_combine(files, identifiers, identifiercolumn="df_id"):
-    """
-    appends one table to another while adding a column to identify which entries came from each table
-    :param files: list of csv files
-    :param identifiers: list of labels to identify original tables
-    :param: identifiercolumn: name of identifiercolumn
-    :return
-    """
-
-    if not isinstance(files, list) or not isinstance(identifiers, list):
-        raise Exception("Either files or identifiers is not a list")
-    for file in files:
-        if not os.path.exists(file):
-            raise Exception(file + " was not found!")
-
-    df_combined = pd.read_csv(files[0])
-    df_combined[identifiercolumn] = identifiers[0]
-
-    for file, identifier in zip(files[1:], identifiers[1:]):
-        nextfile = pd.read_csv(file)
-        nextfile[identifiercolumn] = identifier
-        df_combined = df_combined.append(nextfile)
-
-    return df_combined
-
-
-def mnp_csvlister(folder, notwanted=False, extension=False):
-    """
-    list all species output csv files in an MNP result folder
-    you can provida a list of species that you want to exclude from te returned list
-    :param folder: MNP result folder
-    :param notwanted: list of species to exclude
-    :param extension: return file extensions?
-    :return: list containing filenames or species codes
-    """
-    if type(notwanted) != bool:
-        try:
-            file_list = [
-                file
-                for file in os.listdir(folder)
-                if not (np.isin(file[0:9], notwanted))
-            ]
-            file_list.sort()
-        except Exception as e:
-            print(e)
-            next
-    else:
-        file_list = [file for file in os.listdir(folder)]
-        file_list.sort()
-
-    if not extension:
-        file_list = [f[0:9] for f in file_list]
-
-    file_list = list(set([s for s in file_list if s[:2] == "S0"]))
-    file_list.sort()
-
-    return file_list
-
 
 def progress_bar(iterable, prefix='', suffix='', decimals=1, length=100, fill='#', printEnd="\r"):
     """

csv_tools.py

+import os
+import pandas as pd
+import numpy as np
+
+
+def csv_combine(files, identifiers, identifiercolumn="df_id"):
+    """
+    appends one table to another while adding a column to identify which entries came from each table
+    :param files: list of csv files
+    :param identifiers: list of labels to identify original tables
+    :param: identifiercolumn: name of identifiercolumn
+    :return
+    """
+
+    if not isinstance(files, list) or not isinstance(identifiers, list):
+        raise Exception("Either files or identifiers is not a list")
+    for file in files:
+        if not os.path.exists(file):
+            raise Exception(file + " was not found!")
+
+    df_combined = pd.read_csv(files[0])
+    df_combined[identifiercolumn] = identifiers[0]
+
+    for file, identifier in zip(files[1:], identifiers[1:]):
+        nextfile = pd.read_csv(file)
+        nextfile[identifiercolumn] = identifier
+        df_combined = df_combined.append(nextfile)
+
+    return df_combined
+
+
+def mnp_csvlister(folder, notwanted=False, extension=False):
+    """
+    list all species output csv files in an MNP result folder
+    you can provida a list of species that you want to exclude from te returned list
+    :param folder: MNP result folder
+    :param notwanted: list of species to exclude
+    :param extension: return file extensions?
+    :return: list containing filenames or species codes
+    """
+    if type(notwanted) != bool:
+        try:
+            file_list = [
+                file
+                for file in os.listdir(folder)
+                if not (np.isin(file[0:9], notwanted))
+            ]
+            file_list.sort()
+        except Exception as e:
+            print(e)
+            next
+    else:
+        file_list = [file for file in os.listdir(folder)]
+        file_list.sort()
+
+    if not extension:
+        file_list = [f[0:9] for f in file_list]
+
+    file_list = list(set([s for s in file_list if s[:2] == "S0"]))
+    file_list.sort()
+
+    return file_list