Browse Source

[DATALAD] Recorded changes

Apfelsaft 2 years ago
parent
commit
3b285fe745

+ 17 - 1
code/grid2csv.py

@@ -6,6 +6,11 @@ import re
 input_dir = "outputs/mfa_align_output"
 output_path = "outputs/grid2csv_output"
 
+#creates dataframe with previously dropped entries
+original_df = pd.read_csv("inputs/vandam-data/annotations/cha/converted/BN32_010007_0_0.csv")
+original_df = original_df.dropna(subset = ['transcription'])
+original_df = original_df[original_df['transcription'].str.match(r"[^a-zA-Z]")]
+
 speaker_type_dic = {
         "CHI - words" : "CHI",
         "CHI - phones" : "CHI",
@@ -27,8 +32,9 @@ for file in files:
     print(file)
     grid = pr.TextGrid(file)
 
-    #gets original onset of the sliced recording
+    #gets original onset and offset of the sliced recording
     audio_onset = int(re.split("\D+", file.stem)[1])
+    audio_offset = int(re.split("\D+", file.stem)[2])
 
     #initialize header
     df = pd.DataFrame(columns= ["speaker_id","segment_offset","mwu_type","transcription","speaker_type",
@@ -44,6 +50,16 @@ for file in files:
     
     #populates speaker_type column
     df['speaker_type'] = df['speaker_id'].map(speaker_type_dic)
+
+    #enriches the csv with previously dropped entries corresponsing to the right timestamps
+    orig_df_subset = original_df[(original_df['segment_onset'] >= audio_onset) &
+                         (original_df['segment_offset'] <= audio_offset)]
+
+    df = df.append(orig_df_subset)
+
+    #sort values by segment_onset before exporting
+    df.sort_values(by='segment_onset', inplace= True)
+
     #exports to csv
     df.to_csv("{0}/{1}.csv".format(output_path, file.stem), mode = "x", na_rep= "NA", index= False)
     print("----------------SAVED!-----------------")

+ 1 - 1
outputs/grid2csv_output/BN-0-727249.csv

@@ -1 +1 @@
-../../.git/annex/objects/49/28/MD5E-s101199--f0ef1e67969cef1cedc4d534f65b7860.csv/MD5E-s101199--f0ef1e67969cef1cedc4d534f65b7860.csv
+../../.git/annex/objects/k1/85/MD5E-s104298--03972dfb2675594715bd6929eaf313e3.csv/MD5E-s104298--03972dfb2675594715bd6929eaf313e3.csv

+ 1 - 1
outputs/grid2csv_output/BN-1297003-1913555.csv

@@ -1 +1 @@
-../../.git/annex/objects/2J/Vm/MD5E-s118161--e455d4a37c0927f792dcd1f9c6627603.csv/MD5E-s118161--e455d4a37c0927f792dcd1f9c6627603.csv
+../../.git/annex/objects/G6/FV/MD5E-s122253--5819007f4d16526ec30ed07891ede1cf.csv/MD5E-s122253--5819007f4d16526ec30ed07891ede1cf.csv

+ 1 - 1
outputs/grid2csv_output/BN-727249-1297003.csv

@@ -1 +1 @@
-../../.git/annex/objects/47/gP/MD5E-s103933--c04d33b0486c0d94a012bdf44edfac4e.csv/MD5E-s103933--c04d33b0486c0d94a012bdf44edfac4e.csv
+../../.git/annex/objects/0g/2V/MD5E-s105529--f99080b1a555ede680f060c467ba9dfa.csv/MD5E-s105529--f99080b1a555ede680f060c467ba9dfa.csv