Merge branch 'main' into summary_multi_docs

.flake8

@@ -1,5 +1,5 @@
 [flake8]
-ignore = E203, F401, E402, E501, W503
+extend-ignore = E203, F401, E402, E501, W503
 exclude = .git,__pycache__,.ipynb_checkpoints
 max-line-length = 90
 max-complexity = 18

.flake8_nb

@@ -1,5 +1,5 @@
 [flake8_nb]
-ignore = F401, E402, E501
+extend-ignore = E203, F401, E402, E501
 exclude = .git,__pycache__,.ipynb_checkpoints
 max-line-length = 90
 max-complexity = 18

.github/workflows/ci.yml

@@ -40,3 +40,4 @@ jobs:
         fail_ci_if_error: true
         files: ammico/coverage.xml
         verbose: true
+        token: ${{ secrets.CODECOV_TOKEN }}

.pre-commit-config.yaml

@@ -13,6 +13,6 @@ repos:
     hooks:
     - id: flake8
   - repo: https://github.com/s-weigand/flake8-nb
-    rev: v0.5.0
+    rev: v0.5.3
     hooks:
     - id: flake8-nb

ammico/display.py

@@ -70,7 +70,7 @@ class AnalysisExplorer:
                     [self._middle_picture_frame()],
                     id="Div_middle",
                     style={
-                        "width": "60%",
+                        "width": "50%",
                         "display": "inline-block",
                         "verticalAlign": "top",
                     },
@@ -80,13 +80,13 @@ class AnalysisExplorer:
                     [self._right_output_json()],
                     id="Div_right",
                     style={
-                        "width": "30%",
+                        "width": "45%",
                         "display": "inline-block",
                         "verticalAlign": "top",
                     },
                 ),
             ],
-            style={"width": "80%", "display": "inline-block"},
+            style={"width": "95%", "display": "inline-block"},
         )
         self.app.layout = app_layout
         # add callbacks to app

ammico/text.py

@@ -11,7 +11,6 @@ import pandas as pd
 from bertopic import BERTopic
 from transformers import pipeline
 
-# make widgets work again
 # clean text has weird spaces and separation of "do n't"
 # increase coverage for text
 
@@ -127,6 +126,7 @@ class TextDetector(utils.AnalysisMethod):
         # use the current default model - 03/2023
         model_name = "sshleifer/distilbart-cnn-12-6"
         model_revision = "a4f8f3e"
+        max_number_of_characters = 3000
         pipe = pipeline(
             "summarization",
             model=model_name,
@@ -134,7 +134,8 @@ class TextDetector(utils.AnalysisMethod):
             min_length=5,
             max_length=20,
         )
-        summary = pipe(self.subdict["text_english"])
+        print(self.subdict["text_english"])
+        summary = pipe(self.subdict["text_english"][0:max_number_of_characters])
         self.subdict["text_summary"] = summary[0]["summary_text"]
 
     def text_sentiment_transformers(self):
@@ -143,7 +144,10 @@ class TextDetector(utils.AnalysisMethod):
         model_name = "distilbert-base-uncased-finetuned-sst-2-english"
         model_revision = "af0f99b"
         pipe = pipeline(
-            "text-classification", model=model_name, revision=model_revision
+            "text-classification",
+            model=model_name,
+            revision=model_revision,
+            truncation=True,
         )
         result = pipe(self.subdict["text_english"])
         self.subdict["sentiment"] = result[0]["label"]
@@ -161,7 +165,6 @@ class TextDetector(utils.AnalysisMethod):
             aggregation_strategy="simple",
         )
         result = pipe(self.subdict["text_english"])
-        # self.subdict["entity"] = result
         self.subdict["entity"] = []
         self.subdict["entity_type"] = []
         for entity in result: