nkululeko 0.95.7__py3-none-any.whl → 0.95.9__py3-none-any.whl

nkululeko/autopredict/ap_translate.py

@@ -0,0 +1,39 @@
+"""A translator for text.
+
+Currently based on google translate.
+"""
+
+from nkululeko.utils.util import Util
+
+
+class TextTranslator:
+    """Translator.
+
+    translate text with the google translate model
+    """
+
+    def __init__(self, df, util=None):
+        self.df = df
+        if util is not None:
+            self.util = util
+        else:
+            # create a new util instance
+            # this is needed to access the config and other utilities
+            # in the autopredict module
+            self.util = Util("translator")
+            
+        self.language = self.util.config_val("PREDICT", "target_language", "en")
+        from nkululeko.autopredict.google_translator import GoogleTranslator
+        self.translator = GoogleTranslator(
+            language=self.language,
+            util=self.util,
+        )
+
+    def predict(self, split_selection):
+        self.util.debug(f"translating text for {split_selection} samples")
+        df = self.translator.translate_index(
+            self.df
+        )
+        return_df = self.df.copy()
+        return_df[self.language] = df[self.language].values
+        return return_df

nkululeko/autopredict/google_translator.py

@@ -0,0 +1,63 @@
+import os
+
+import pandas as pd
+import torch
+from tqdm import tqdm
+
+import asyncio
+from googletrans import Translator
+
+import audeer
+import audiofile
+
+from nkululeko.utils.util import Util
+
+import httpx
+
+class GoogleTranslator:
+    def __init__(self, language="en", util=None):
+        self.language = language
+        self.util = util
+
+    async def translate_text(self, text):
+        async with Translator() as translator:
+            result = translator.translate(text, dest="en")
+            return (await result).text
+
+    def translate_index(self, df:pd.DataFrame) ->  pd.DataFrame:
+        """Transcribe the audio files in the given index.
+
+        :param index: Index containing tuples of (file, start, end).
+        :return: DataFrame with transcriptions indexed by the original index.
+        :rtype: pd.DataFrame
+        """
+        file_name = ""
+        seg_index = 0
+        translations = []
+        translator_cache = audeer.mkdir(
+            audeer.path(self.util.get_path("cache"), "translations"))
+        file_name = ""
+        for idx, row in tqdm(df.iterrows(), total=len(df)):
+            file = idx[0]
+            start = idx[1]
+            end = idx[2]
+            if file != file_name:
+                file_name = file
+                seg_index = 0
+            cache_name = audeer.basename_wo_ext(file)+str(seg_index)
+            cache_path = audeer.path(translator_cache, cache_name + ".json")
+            if os.path.isfile(cache_path):
+                translation = self.util.read_json(cache_path)["translation"]
+            else:
+                text = row['text']
+                translation = asyncio.run(self.translate_text(text))
+                self.util.save_json(cache_path, 
+                                {"translation": translation, 
+                                 "file": file, 
+                                 "start": start.total_seconds(), 
+                                 "end": end.total_seconds()})
+            translations.append(translation)
+            seg_index += 1
+
+        df = pd.DataFrame({self.language:translations}, index=df.index)
+        return df

nkululeko/constants.py

@@ -1,2 +1,2 @@
-VERSION="0.95.7"
+VERSION="0.95.9"
 SAMPLING_RATE = 16000

nkululeko/experiment.py

@@ -574,6 +574,11 @@ class Experiment:
 
                 predictor = TextPredictor(df, self.util)
                 df = predictor.predict(sample_selection)
+            elif target == "translation":
+                from nkululeko.autopredict.ap_translate import TextTranslator
+
+                predictor = TextTranslator(df, self.util)
+                df = predictor.predict(sample_selection)
             elif target == "arousal":
                 from nkululeko.autopredict.ap_arousal import ArousalPredictor
 

nkululeko/plots.py

@@ -28,7 +28,10 @@ class Plots:
         self.with_ccc = eval(self.util.config_val("PLOT", "ccc", "False"))
         self.type_s = "samples"
 
-    def plot_distributions_speaker(self, df):
+    def plot_distributions_speaker(self, df: pd.DataFrame):
+        if df.empty:
+            self.util.warn("plot_distributions_speaker: empty DataFrame, nothing to plot")
+            return
         self.type_s = "speaker"
         df_speakers = pd.DataFrame()
         pd.options.mode.chained_assignment = None  # default='warn'
@@ -87,7 +90,10 @@ class Plots:
 
         self.plot_distributions(df_speakers, type_s="speakers")
 
-    def plot_distributions(self, df, type_s="samples"):
+    def plot_distributions(self, df: pd.DataFrame, type_s: str = "samples"):
+        if df.empty:
+            self.util.warn("plot_distributions: empty DataFrame, nothing to plot")
+            return
         class_label, df = self._check_binning("class_label", df)
         value_counts_conf = self.util.config_val("EXPL", "value_counts", False)
         if not isinstance(value_counts_conf, str):

nkululeko/utils/util.py

@@ -189,8 +189,11 @@ class Util:
 
     def is_categorical(self, pd_series):
         """Check if a dataframe column is categorical."""
-        return pd_series.dtype.name == "object" or isinstance(
-            pd_series.dtype, pd.CategoricalDtype
+        return (
+            pd_series.dtype.name == "object"
+            or pd_series.dtype.name == "bool"
+            or isinstance(pd_series.dtype, pd.CategoricalDtype)
+            or isinstance(pd_series.dtype, pd.BooleanDtype)
         )
 
     def get_name(self):

{nkululeko-0.95.7.dist-info → nkululeko-0.95.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nkululeko
-Version: 0.95.7
+Version: 0.95.9
 Summary: Machine learning audio prediction experiments based on templates
 Home-page: https://github.com/felixbur/nkululeko
 Author: Felix Burkhardt

{nkululeko-0.95.7.dist-info → nkululeko-0.95.9.dist-info}/RECORD

@@ -4,13 +4,13 @@ nkululeko/aug_train.py,sha256=wpiHCJ7zsW38kumg3ypwXZe2HQrhUblAnv7P2QeJnAc,3525
 nkululeko/augment.py,sha256=3RzaxB3gRxovgJVjHXi0glprW01J7RaHhUkqotW2T3U,2955
 nkululeko/balance.py,sha256=r7opXbrqAipm2euPPaOmLlA5J10p2bHQgO5kWk2x9ro,8702
 nkululeko/cacheddataset.py,sha256=XFpWZmbJRg0pvhnIgYf0TkclxllD-Fctu-Ol0PF_00c,969
-nkululeko/constants.py,sha256=6jfPRCrnqqRsGqz83bT34_5gPBbTiIAsnhzVWUrKXl4,39
+nkululeko/constants.py,sha256=t_C_hQqVC1idXJB6HHr1m7ZtCYC5JVvqhYrVLRhzwIw,39
 nkululeko/demo-ft.py,sha256=iD9Pzp9QjyAv31q1cDZ75vPez7Ve8A4Cfukv5yfZdrQ,770
 nkululeko/demo.py,sha256=tu7Al2l5MCLVegkDC-NE2wcuc_YE7NRbgOlPW3yhGEs,4940
 nkululeko/demo_feats.py,sha256=BvZjeNFTlERIRlq34OHM4Z96jdDQAhB01BGQAUcX9dM,2026
 nkululeko/demo_predictor.py,sha256=lDF-xOxRdEAclOmbepAYg-BQXQdGkHfq2n74PTIoop8,4872
 nkululeko/ensemble.py,sha256=71V-rre61H3J4sh7lu-OTo4I2_g7mm_rQxwW1ARDHgY,12782
-nkululeko/experiment.py,sha256=BAc220lktt_tvifl-m-ZIPO7Nwi-HzDBNyTfjPDbQkE,38397
+nkululeko/experiment.py,sha256=TG9G9kSETT_R8d92aRKMMsb0HRGyM_GBFHBsU9A6ppw,38633
 nkululeko/explore.py,sha256=PjNcLuPdvWqCqYXUvGhd0hBijIhzdyi3ED1RF6o5Gjk,4212
 nkululeko/export.py,sha256=U-V4acxtuL6qKt6oAsVcM5TTeWogYUJ3GU-lA6rq6d4,4336
 nkululeko/feature_extractor.py,sha256=CsKmBoxwNClRGu20ox_eCxMG4u_1OH8Y83FYw7GfUwA,4230
@@ -24,7 +24,7 @@ nkululeko/nkuluflag.py,sha256=_83LqLr2bSHjnVJuPeSAHCIyuiIbRxgpFKW6CwanWFM,3728
 nkululeko/nkululeko.py,sha256=6ALPMMIz6l0O3IRaP0q4b59ZUxpfzNqLQUqZMf5t3Zo,1976
 nkululeko/optim.py,sha256=Pn_02irXYJJmNG1yWA9GImHirpbXXywV61MalZb2wVA,1658
 nkululeko/optimizationrunner.py,sha256=UfWU_gOPaHUVjvYaw3AoF9HoDGYxIjbCyTGmi1PVu3s,44283
-nkululeko/plots.py,sha256=rVkOGWB7yLkZ1dGg_MXeKhPOtiquiYIyCam4KYOdJQY,27519
+nkululeko/plots.py,sha256=DnTJHmz50vphnTiazCy2J6k0wP0-MRWir7gj7i_WKXM,27808
 nkululeko/predict.py,sha256=PWv1Pc39lrxqqIWrYszVk5SL37dDL93CHgcruItNID8,2211
 nkululeko/resample.py,sha256=rn3-M1A-iwVGibfQNGyeYNa7briD24lIN9Szq_1uTJo,5194
 nkululeko/runmanager.py,sha256=YtGQP0UyyQTKkilncB1XYM-T8oatzGcZEOcj5SorjJw,8902
@@ -52,8 +52,10 @@ nkululeko/autopredict/ap_sid.py,sha256=b_JwVWlqcwdC7acU9Q7mExuOJKUn6qdlmQTm8pmmp
 nkululeko/autopredict/ap_snr.py,sha256=cjc0pUsCN_RacTw1UBR2cGY9t_um48f2cjo3QJDn7bw,1111
 nkululeko/autopredict/ap_stoi.py,sha256=csv9qCcRmieHAhypszqGoGt9r3biM8IYPgcTwp9GIFM,1188
 nkululeko/autopredict/ap_text.py,sha256=zaz9qIg90-ghZhBe1ka0HoUnap6s6RyopUKoCpttHOU,1333
+nkululeko/autopredict/ap_translate.py,sha256=3yxNQmysAB3GP84YjFg_9Wc5yz0iXZXxrL5VZpEyyiI,1138
 nkululeko/autopredict/ap_valence.py,sha256=9S06SpO_zXKSpkf0InHYYXZcD9HDGoCJ6UPkn__eBAg,1027
 nkululeko/autopredict/estimate_snr.py,sha256=1k9-XadABudnsNOeFZD_Fg0E64-GUQVS7JEp82MLQS4,4995
+nkululeko/autopredict/google_translator.py,sha256=at5v7vWbP9UwXDVqVCqai4SKz-XuazpeeFsptSGrBUU,2114
 nkululeko/autopredict/whisper_transcriber.py,sha256=DWDvpRaV5KmUF18ojPEvxnVXm_h_nWyY-TfW2Ngd5N8,2941
 nkululeko/autopredict/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/autopredict/tests/test_whisper_transcriber.py,sha256=ilas6j3OUvq_xnQCRZgytQCtyrpNU6tvG5a8kPvVKBQ,5085
@@ -133,10 +135,10 @@ nkululeko/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nkululeko/utils/files.py,sha256=SrrYaU7AB80MZHiV1jcB0h_zigvYLYgSVNTXV4ao38g,4593
 nkululeko/utils/stats.py,sha256=3Fyx8q8BSKYmiufT6OkRug9RATWmGrr9BaX_y8jziWo,3074
 nkululeko/utils/unzip.py,sha256=G68f5120TjwACZC3bQcneMniddnwubPbBdMc2L5KBOo,1206
-nkululeko/utils/util.py,sha256=yHgzfj-8ncgCvyrrrH_NDWCh6VmhAqVYY6Vlgyg-c6E,18585
-nkululeko-0.95.7.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
-nkululeko-0.95.7.dist-info/METADATA,sha256=s_XLh9XUEm_NRApCwnUc8QKkRHWqlva7yxY8Jce0vSI,21998
-nkululeko-0.95.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-nkululeko-0.95.7.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
-nkululeko-0.95.7.dist-info/top_level.txt,sha256=bf1k1YKkqcXemNX_cUgoyKqQ3_GVErPqAY-53J36jkM,19
-nkululeko-0.95.7.dist-info/RECORD,,
+nkululeko/utils/util.py,sha256=s7Hd7Ju1r3_WCw8gLD9YK4O6k3S_WhFcN2-XZBSctSM,18705
+nkululeko-0.95.9.dist-info/licenses/LICENSE,sha256=0zGP5B_W35yAcGfHPS18Q2B8UhvLRY3dQq1MhpsJU_U,1076
+nkululeko-0.95.9.dist-info/METADATA,sha256=WhITXnJHYD5GhyATjEb7kJhmMecWRu-BeMBw7pSWNdc,21998
+nkululeko-0.95.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nkululeko-0.95.9.dist-info/entry_points.txt,sha256=lNTkFEdh6Kjo5o95ZAWf_0Lq-4ztGoAoMVSDuPtuyS0,442
+nkululeko-0.95.9.dist-info/top_level.txt,sha256=bf1k1YKkqcXemNX_cUgoyKqQ3_GVErPqAY-53J36jkM,19
+nkululeko-0.95.9.dist-info/RECORD,,