fix: missing dependency, obsolete keyword, dash maintenance, demo notebook for new summary

ammico/display.py

@@ -94,7 +94,6 @@ class AnalysisExplorer:
             State("left_select_id", "options"),
             State("left_select_id", "value"),
             State("Dropdown_select_Detector", "value"),
-            State("setting_Text_analyse_text", "value"),
             State("setting_privacy_env_var", "value"),
             State("setting_Emotion_emotion_threshold", "value"),
             State("setting_Emotion_race_threshold", "value"),
@@ -157,14 +156,6 @@ class AnalysisExplorer:
                     id="settings_TextDetector",
                     style={"display": "none"},
                     children=[
-                        dbc.Row(
-                            dcc.Checklist(
-                                ["Analyse text"],
-                                ["Analyse text"],
-                                id="setting_Text_analyse_text",
-                                style={"margin-bottom": "10px"},
-                            ),
-                        ),
                         # row 1
                         dbc.Row(
                             dbc.Col(
@@ -344,7 +335,7 @@ class AnalysisExplorer:
             port (int, optional): The port number to run the server on (default: 8050).
         """
 
-        self.app.run_server(debug=True, port=port)
+        self.app.run(debug=True, port=port)
 
     # Dash callbacks
     def update_picture(self, img_path: str):
@@ -375,16 +366,15 @@ class AnalysisExplorer:
         }
 
         if setting_input == "TextDetector":
-            return display_flex, display_none, display_none, display_none
+            return display_flex, display_none, display_none
 
         if setting_input == "EmotionDetector":
-            return display_none, display_flex, display_none, display_none
+            return display_none, display_flex, display_none
-
         if setting_input == "ColorDetector":
-            return display_none, display_none, display_flex, display_none
+            return display_none, display_none, display_flex
 
         else:
-            return display_none, display_none, display_none, display_none
+            return display_none, display_none, display_none
 
     def _right_output_analysis(
         self,
@@ -392,7 +382,6 @@ class AnalysisExplorer:
         all_img_options: dict,
         current_img_value: str,
         detector_value: str,
-        settings_text_analyse_text: list,
         setting_privacy_env_var: str,
         setting_emotion_emotion_threshold: int,
         setting_emotion_race_threshold: int,
@@ -426,12 +415,8 @@ class AnalysisExplorer:
         identify_function = identify_dict[detector_value]
 
         if detector_value == "TextDetector":
-            analyse_text = (
-                True if settings_text_analyse_text == ["Analyse text"] else False
-            )
             detector_class = identify_function(
                 image_copy,
-                analyse_text=analyse_text,
                 accept_privacy=(
                     setting_privacy_env_var
                     if setting_privacy_env_var

ammico/notebooks/DemoNotebook_ammico.ipynb

@@ -104,7 +104,8 @@
     "import ammico\n",
     "\n",
     "# for displaying a progress bar\n",
-    "from tqdm import tqdm"
+    "from tqdm import tqdm\n",
+    "import os"
    ]
   },
   {
@@ -140,7 +141,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# os.environ[\"GOOGLE_APPLICATION_CREDENTIALS\"] = \"/content/drive/MyDrive/misinformation-data/misinformation-campaign-981aa55a3b13.json\""
+    "os.environ[\"GOOGLE_APPLICATION_CREDENTIALS\"] = (\n",
+    "    \"/home/inga/projects/misinformation-project/misinformation-notes/misinformation-campaign-981aa55a3b13.json\"\n",
+    ")"
    ]
   },
   {
@@ -171,6 +174,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "data_path = \"./data-test\"\n",
     "image_dict = ammico.find_files(\n",
     "    # path = \"/content/drive/MyDrive/misinformation-data/\",\n",
     "    path=str(data_path),\n",
@@ -337,7 +341,7 @@
     "    enumerate(image_dict.keys()), total=len(image_dict)\n",
     "):  # loop through all images\n",
     "    image_dict[key] = ammico.TextDetector(\n",
-    "        image_dict[key], analyse_text=True\n",
+    "        image_dict[key]\n",
     "    ).analyse_image()  # analyse image with EmotionDetector and update dict\n",
     "\n",
     "    if (\n",
@@ -361,23 +365,12 @@
    "outputs": [],
    "source": [
     "# initialize the models\n",
-    "image_summary_detector = ammico.SummaryDetector(\n",
+    "model = ammico.MultimodalSummaryModel()\n",
-    "    subdict=image_dict, analysis_type=\"summary\", model_type=\"base\"\n",
+    "image_summary_detector = ammico.ImageSummaryDetector(\n",
+    "    subdict=image_dict, summary_model=model\n",
     ")\n",
     "\n",
-    "# run the analysis without having to re-iniatialize the model\n",
+    "image_summary_detector.analyse_images(analysis_type=\"summary\")"
-    "for num, key in tqdm(\n",
-    "    enumerate(image_dict.keys()), total=len(image_dict)\n",
-    "):  # loop through all images\n",
-    "    image_dict[key] = image_summary_detector.analyse_image(\n",
-    "        subdict=image_dict[key], analysis_type=\"summary\"\n",
-    "    )  # analyse image with SummaryDetector and update dict\n",
-    "\n",
-    "    if (\n",
-    "        num % dump_every == 0 | num == len(image_dict) - 1\n",
-    "    ):  # save results every dump_every to dump_file\n",
-    "        image_df = ammico.get_dataframe(image_dict)\n",
-    "        image_df.to_csv(dump_file)"
    ]
   },
   {
@@ -394,6 +387,7 @@
    "outputs": [],
    "source": [
     "# initialize the models\n",
+    "# currently this does not work because of the way the summary detector is implemented\n",
     "image_summary_detector = ammico.SummaryDetector(\n",
     "    subdict=image_dict, analysis_type=\"summary\", model_type=\"base\"\n",
     ")\n",

ammico/text.py

@@ -67,7 +67,6 @@ class TextDetector(AnalysisMethod):
     def __init__(
         self,
         subdict: dict,
-        analyse_text: bool = False,
         skip_extraction: bool = False,
         accept_privacy: str = "PRIVACY_AMMICO",
     ) -> None:
@@ -76,8 +75,6 @@ class TextDetector(AnalysisMethod):
         Args:
             subdict (dict): Dictionary containing file name/path, and possibly previous
                 analysis results from other modules.
-            analyse_text (bool, optional): Decide if extracted text will be further subject
-                to analysis. Defaults to False.
             skip_extraction (bool, optional): Decide if text will be extracted from images or
                 is already provided via a csv. Defaults to False.
             accept_privacy (str, optional): Environment variable to accept the privacy
@@ -96,17 +93,13 @@ class TextDetector(AnalysisMethod):
                 "Privacy disclosure not accepted - skipping text detection."
             )
         self.translator = Translator(raise_exception=True)
-        if not isinstance(analyse_text, bool):
-            raise ValueError("analyse_text needs to be set to true or false")
-        self.analyse_text = analyse_text
         self.skip_extraction = skip_extraction
         if not isinstance(skip_extraction, bool):
             raise ValueError("skip_extraction needs to be set to true or false")
         if self.skip_extraction:
             print("Skipping text extraction from image.")
             print("Reading text directly from provided dictionary.")
-        if self.analyse_text:
+        self._initialize_spacy()
-            self._initialize_spacy()
 
     def set_keys(self) -> dict:
         """Set the default keys for text analysis.
@@ -183,7 +176,7 @@ class TextDetector(AnalysisMethod):
             self._truncate_text()
             self.translate_text()
             self.remove_linebreaks()
-            if self.analyse_text and self.subdict["text_english"]:
+            if self.subdict["text_english"]:
                 self._run_spacy()
         return self.subdict
 

pyproject.toml

@@ -47,6 +47,7 @@ dependencies = [
     "spacy",
     "tensorflow<2.15", # instead of <=2.16.0 to make it compatible with CUDA 11.8, may change after updating CUDA version.
     "tf-keras",
+    "torchvision",
     "tqdm",
     "transformers>=4.54",
     "webcolors",