Import fixes (#160)

* Replaced .append with pd.concat for pandas upgrade * Added resampy to poetry to fix librosa dependencies * Fixed return type mismatches for Microfaune and BirdNET --------- Co-authored-by: TQ Zhang <[email protected]>
UCSD-E4E · Nov 17, 2023 · 3ac09a5 · 3ac09a5
1 parent 7d0aa42
commit 3ac09a5
Show file tree

Hide file tree

Showing 8 changed files with 43 additions and 21 deletions.
diff --git a/PyHa/IsoAutio.py b/PyHa/IsoAutio.py
@@ -990,7 +990,7 @@ def generate_automated_labels_microfaune(
             if annotations.empty:
                 annotations = new_entry
             else:
-                annotations = annotations.append(new_entry)
+                annotations = pd.concat([annotations, new_entry])
         except KeyboardInterrupt:
             exit("Keyboard interrupt")
         except BaseException as e:
@@ -1127,7 +1127,7 @@ def generate_automated_labels_tweetynet(
             if annotations.empty:
                 annotations = new_entry
             else:
-                annotations = annotations.append(new_entry)
+                annotations = pd.concat([annotations, new_entry])
         except KeyboardInterrupt:
             exit("Keyboard interrupt")
         except BaseException as e:

diff --git a/PyHa/birdnet_lite/analyze.py b/PyHa/birdnet_lite/analyze.py
@@ -83,13 +83,14 @@ def splitSignal(sig, rate, overlap, seconds=3.0, minlen=1.5):
 def readAudioData(path, overlap, sample_rate=48000):
 
     print('READING AUDIO DATA...', end=' ', flush=True)
-
-    # Open file with librosa (uses ffmpeg or libav)
+    print("Path: ", path)
+    # Open file with librosa (uses ffmanaeg or libav)
     try:
         sig, rate = librosa.load(path, sr=sample_rate, mono=True, res_type='kaiser_fast')
         clip_length = librosa.get_duration(y=sig, sr=rate)
-    except:
-        return 0
+    except Exception as e:
+        print(e)
+        return (0, 0)
     # Split audio into 3-second chunks
     chunks = splitSignal(sig, rate, overlap)
 

diff --git a/PyHa/microfaune_package/microfaune/audio.py b/PyHa/microfaune_package/microfaune/audio.py
@@ -124,7 +124,7 @@ def create_spec(data, fs, n_mels=32, n_fft=2048, hop_len=1024):
     """
     # Calculate spectrogram
     S = librosa.feature.melspectrogram(
-      data, sr=fs, n_fft=n_fft, hop_length=hop_len, n_mels=n_mels)
+    y=data, sr=fs, n_fft=n_fft, hop_length=hop_len, n_mels=n_mels)
     S = S.astype(np.float32)
 
     # Convert power to dB

diff --git a/PyHa/statistics.py b/PyHa/statistics.py
@@ -263,25 +263,25 @@ def automated_labeling_statistics(
                 if statistics_df.empty:
                     statistics_df = clip_stats_df
                 else:
-                    statistics_df = statistics_df.append(clip_stats_df)
+                    statistics_df = pd.concat([statistics_df,clip_stats_df])
             elif stats_type == "IoU":
                 IoU_Matrix = clip_IoU(clip_automated_df, clip_manual_df)
                 clip_stats_df = matrix_IoU_Scores(
                     IoU_Matrix, clip_manual_df, threshold)
                 if statistics_df.empty:
                     statistics_df = clip_stats_df
                 else:
-                    statistics_df = statistics_df.append(clip_stats_df)
+                    statistics_df = pd.concat([statistics_df, clip_stats_df])
         except BaseException as e:
             num_errors += 1
             #print("Something went wrong with: " + clip)
-            #print(e)
+            print(e)
             continue
         if num_processed % 50 == 0:
             print("Processed", num_processed, "clips in", int((time.time() - start_time) * 10) / 10.0, 'seconds')
             start_time = time.time()
     if num_errors > 0:
-        checkVerbose("Something went wrong with" + num_errors + "clips out of" + str(len(clips)) + "clips", verbose)
+        checkVerbose(f"Something went wrong with {num_errors} clips out of {len(clips)} clips", verbose)
     statistics_df.reset_index(inplace=True, drop=True)
     return statistics_df
 
@@ -751,7 +751,7 @@ def dataset_Catch(automated_df, manual_df):
         if manual_df_with_Catch.empty:
             manual_df_with_Catch = clip_manual_df
         else:
-            manual_df_with_Catch = manual_df_with_Catch.append(clip_manual_df)
+            manual_df_with_Catch = pd.concat([manual_df_with_Catch,clip_manual_df])
     # Resetting the indices
     manual_df_with_Catch.reset_index(inplace=True, drop=True)
     return manual_df_with_Catch
@@ -825,7 +825,7 @@ def clip_statistics(
             clip_statistics = automated_labeling_statistics(temp_automated_class_df, temp_manual_class_df, stats_type = stats_type, threshold = threshold)
         else:
             temp_df = automated_labeling_statistics(temp_automated_class_df, temp_manual_class_df, stats_type = stats_type, threshold = threshold)
-            clip_statistics = clip_statistics.append(temp_df)
+            clip_statistics = pd.concat([clip_statistics,temp_df])
     clip_statistics.reset_index(inplace=True,drop=True)
     return clip_statistics
 
@@ -860,6 +860,6 @@ def class_statistics(clip_statistics):
             class_statistics = global_statistics(class_df, manual_id = class_)
         else:
             temp_df = global_statistics(class_df, manual_id = class_)
-            class_statistics = class_statistics.append(temp_df)
+            class_statistics = pd.concat([class_statistics,temp_df])
     class_statistics.reset_index(inplace=True,drop=True)
     return class_statistics
diff --git a/PyHa/tweetynet_package/tweetynet/Load_data_functions.py b/PyHa/tweetynet_package/tweetynet/Load_data_functions.py
@@ -216,12 +216,12 @@ def predictions_to_kaleidoscope(predictions, SIGNAL, audio_dir, audio_file, manu
         raise BaseException("No birds were detected!!")
 
     if offset.iloc[0] != 0:
-        kaleidoscope_df.append(pd.DataFrame({"OFFSET": [0], "DURATION": [offset.iloc[0]]}))
-    kaleidoscope_df.append(intermediary_df[intermediary_df["DURATION"] >= 2*time_bin_seconds])
+        pd.concat([kaleidoscope_df,pd.DataFrame({"OFFSET": [0], "DURATION": [offset.iloc[0]]})])
+    pd.concat([kaleidoscope_df,intermediary_df[intermediary_df["DURATION"] >= 2*time_bin_seconds]])
 
     if offset.iloc[-1] < predictions.iloc[-1]["time_bins"]:
-        kaleidoscope_df.append(pd.DataFrame({"OFFSET": [offset.iloc[-1]], "DURATION": [predictions.iloc[-1]["time_bins"] + 
-                                predictions.iloc[1]["time_bins"]]}))
+        pd.concat([kaleidoscope_df,pd.DataFrame({"OFFSET": [offset.iloc[-1]], "DURATION": [predictions.iloc[-1]["time_bins"] + 
+                                predictions.iloc[1]["time_bins"]]})])
 
     kaleidoscope_df = pd.concat(kaleidoscope_df)
     kaleidoscope_df = kaleidoscope_df.reset_index(drop=True)

diff --git a/PyHa/tweetynet_package/tweetynet/TweetyNetModel.py b/PyHa/tweetynet_package/tweetynet/TweetyNetModel.py
@@ -111,7 +111,7 @@ def predict(self, test_dataset, model_weights=None, norm=False):
                 bins = st_time + (int(uids[0].split("_")[0])*window_size)
                 d = {"uid": uids[0], "pred": pred, "label": labels, "time_bins": bins}
                 new_preds = pd.DataFrame(d)
-                predictions = predictions.append(new_preds)
+                predictions = pd.concat([predictions, new_preds])
 
         if norm:
             local_score = self.normalize(local_score, 0, 1)

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -59,4 +59,5 @@ tensorflow-cpu-aws = { version = "^2.13.0", platform = "linux", markers = "platf
 tensorflow-io-gcs-filesystem = [
     { version = ">= 0.23.1", markers = "platform_machine!='arm64' or platform_system!='Darwin'" },
     { version = "< 0.32.0", markers = "platform_system == 'Windows'" }
-]
+]
+resampy = "^0.4.2"