fixed errors in documentation (#163)

* fixed errors in documentation

* fixed croppost.py

ammico/cropposts.py

@@ -325,13 +325,15 @@ def crop_media_posts(
 
     # get the reference images with regions that signify areas to crop
     ref_views = []
-    for ref_file in ref_files:
-        ref_view = cv2.imread(ref_file)
+    for ref_file in ref_files.values():
+        ref_file_path = ref_file["filename"]
+        ref_view = cv2.imread(ref_file_path)
         ref_views.append(ref_view)
     # parse through the social media posts to be cropped
-    for crop_file in files:
-        view = cv2.imread(crop_file)
-        print("Doing file {}".format(crop_file))
+    for crop_file in files.values():
+        crop_file_path = crop_file["filename"]
+        view = cv2.imread(crop_file_path)
+        print("Doing file {}".format(crop_file_path))
         crop_view = crop_posts_from_refs(
             ref_views,
             view,
@@ -341,7 +343,7 @@ def crop_media_posts(
         )
         if crop_view is not None:
             # save the image to the provided folder
-            filename = ntpath.basename(crop_file)
+            filename = ntpath.basename(crop_file_path)
             save_path = os.path.join(save_crop_dir, filename)
             save_path = save_path.replace("\\", "/")
             cv2.imwrite(save_path, crop_view)

ammico/notebooks/cropposts.ipynb

@@ -77,7 +77,7 @@
    "source": [
     "# load ref view for cropping the same type social media posts images.\n",
     "# substitute the below paths for your samples\n",
-    "path_ref = \"/content/ref/ref-00.png\"\n",
+    "path_ref = \"../data/ref/ref-00.png\"\n",
     "ref_view = cv2.imread(path_ref)\n",
     "RGB_ref_view = cv2.cvtColor(ref_view, cv2.COLOR_BGR2RGB)\n",
     "plt.figure(figsize=(10, 15))\n",
@@ -133,24 +133,16 @@
    "outputs": [],
    "source": [
     "\n",
-    "crop_dir = \"/content/drive/MyDrive/misinformation-data/\"\n",
-    "ref_dir = \"/content/ref/\"\n",
-    "save_crop_dir = \"/content/drive/MyDrive/misinformation-data/crop/\"\n",
+    "crop_dir = \"../data/\"\n",
+    "ref_dir = \"../data/ref/\"\n",
+    "save_crop_dir = \"../data/crop/\"\n",
     "\n",
-    "files = ammico.find_files(path=crop_dir,limit=10,)\n",
+    "files = ammico.find_files(path=crop_dir,limit=10,recursive=False)\n",
     "ref_files = ammico.find_files(path=ref_dir, limit=100)\n",
     "\n",
     "ammico.crop_media_posts(files, ref_files, save_crop_dir, plt_match=True, plt_crop=False, plt_image=False)\n",
     "print(\"Batch cropping images done\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b3b3c1ad",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -169,7 +161,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

ammico/test/test_cropposts.py

@@ -2,10 +2,11 @@
 import cv2
 import pytest
 import numpy as np
+import ammico.utils as utils
 
 
-TEST_IMAGE_1 = "pic1.png"
-TEST_IMAGE_2 = "pic2.png"
+TEST_IMAGE_1 = "crop_test_files/pic1.png"
+TEST_IMAGE_2 = "crop_test_ref_files/pic2.png"
 
 
 @pytest.fixture
@@ -75,8 +76,9 @@ def test_paste_image_and_comment(open_images):
 
 
 def test_crop_media_posts(get_path, tmp_path):
-    files = [get_path + TEST_IMAGE_1]
-    ref_files = [get_path + TEST_IMAGE_2]
+    print(get_path)
+    files = utils.find_files(path=get_path + "crop_test_files/")
+    ref_files = utils.find_files(path=get_path + "crop_test_ref_files/")
     crpo.crop_media_posts(files, ref_files, tmp_path)
     assert len(list(tmp_path.iterdir())) == 1
     # now check that image in tmp_path is the cropped one

docs/source/notebooks/DemoNotebook_ammico.ipynb

@@ -220,16 +220,9 @@
     "\n",
     "The user can set if the text should be further summarized, and analyzed for sentiment and named entity recognition, by setting the keyword `analyse_text` to `True` (the default is `False`). If set, the transformers pipeline is used for each of these tasks, with the default models as of 03/2023. Other models can be selected by setting the optional keyword `model_names` to a list of selected models, on for each task: `model_names=[\"sshleifer/distilbart-cnn-12-6\", \"distilbert-base-uncased-finetuned-sst-2-english\", \"dbmdz/bert-large-cased-finetuned-conll03-english\"]` for summary, sentiment, and ner. To be even more specific, revision numbers can also be selected by specifying the optional keyword `revision_numbers` to a list of revision numbers for each model, for example `revision_numbers=[\"a4f8f3e\", \"af0f99b\", \"f2482bf\"]`. \n",
     "\n",
-    "Please note that for the Google Cloud Vision API (the TextDetector class) you need to set a key in order to process the images. This key is ideally set as an environment variable using for example"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "os.environ[\"GOOGLE_APPLICATION_CREDENTIALS\"] = \"misinformation-campaign-981aa55a3b13.json\"\n"
+    "Please note that for the Google Cloud Vision API (the TextDetector class) you need to set a key in order to process the images. This key is ideally set as an environment variable using for example:\n",
+    "\n",
+    "`os.environ[\"GOOGLE_APPLICATION_CREDENTIALS\"] = \"misinformation-campaign-981aa55a3b13.json\"`"
    ]
   },
   {

docs/source/notebooks/Example multimodal.ipynb

@@ -45,6 +45,21 @@
     "    drive.mount(\"/content/drive\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9d58a23e",
+   "metadata": {
+    "nbsphinx": "hidden"
+   },
+   "outputs": [],
+   "source": [
+    "# if there is not enough space on your hard drive, clear the cache folder\n",
+    "# this cell will delete all your cache!\n",
+    "!rm -rf ~/.cache\n",
+    "!mkdir ~/.cache"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -531,7 +546,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,