Update Predict_XAI.ipynb

074aed88 · Ludovic Moncla · 6fc7b4e7 · 074aed88
Commit 074aed88 authored 2 years ago by Ludovic Moncla
--- a/notebooks/Predict_XAI.ipynb
+++ b/notebooks/Predict_XAI.ipynb
@@ -738,19 +738,113 @@
    },
    {
      "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 119,
      "metadata": {},
      "outputs": [],
      "source": [
-        "edda_par_path = \"/Users/lmoncla/Nextcloud-LIRIS/GEODE/GEODE - Partage consortium/Corpus/EDdA/EDdA_dataset_articles.tsv\"\n",
+        "edda_par_path = \"/Users/lmoncla/Nextcloud-LIRIS/GEODE/GEODE - Partage consortium/Corpus/EDdA/EDdA_parallel_dataset_articles.tsv\"\n",
        "df_EDdA_par = pd.read_csv(edda_par_path, sep=\"\\t\")"
      ]
    },
    {
      "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 120,
      "metadata": {},
-      "outputs": [],
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>id</th>\n",
+              "      <th>tome</th>\n",
+              "      <th>filename</th>\n",
+              "      <th>content</th>\n",
+              "      <th>nb_words</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>T1article100</td>\n",
+              "      <td>T1</td>\n",
+              "      <td>article100</td>\n",
+              "      <td>ABATAGE, s. m. On dit dans un chantier &amp; sur\\n...</td>\n",
+              "      <td>64</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>T1article1016</td>\n",
+              "      <td>T1</td>\n",
+              "      <td>article1016</td>\n",
+              "      <td>AFFILIATION, s. f. (Jurispr.) s'est dit par le...</td>\n",
+              "      <td>69</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>T1article1036</td>\n",
+              "      <td>T1</td>\n",
+              "      <td>article1036</td>\n",
+              "      <td>AFFLUENT, adj. terme de rivieres, se dit d'une...</td>\n",
+              "      <td>50</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>T1article1038</td>\n",
+              "      <td>T1</td>\n",
+              "      <td>article1038</td>\n",
+              "      <td>AFFORAGE, s. terme de Droit, qui se prend dans...</td>\n",
+              "      <td>83</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>T1article1039</td>\n",
+              "      <td>T1</td>\n",
+              "      <td>article1039</td>\n",
+              "      <td>AFFOUAGE, s. terme de Coûtumes, qui signifie l...</td>\n",
+              "      <td>27</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "              id tome     filename  \\\n",
+              "0   T1article100   T1   article100   \n",
+              "1  T1article1016   T1  article1016   \n",
+              "2  T1article1036   T1  article1036   \n",
+              "3  T1article1038   T1  article1038   \n",
+              "4  T1article1039   T1  article1039   \n",
+              "\n",
+              "                                             content  nb_words  \n",
+              "0  ABATAGE, s. m. On dit dans un chantier & sur\\n...        64  \n",
+              "1  AFFILIATION, s. f. (Jurispr.) s'est dit par le...        69  \n",
+              "2  AFFLUENT, adj. terme de rivieres, se dit d'une...        50  \n",
+              "3  AFFORAGE, s. terme de Droit, qui se prend dans...        83  \n",
+              "4  AFFOUAGE, s. terme de Coûtumes, qui signifie l...        27  "
+            ]
+          },
+          "execution_count": 120,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
      "source": [
        "df_EDdA_par.head()"
      ]
@@ -1263,7 +1357,7 @@
        }
      ],
      "source": [
-        "word_attributions = cls_explainer(content if len(content) < 512 else content[:512])\n",
+        "word_attributions = cls_explainer(content[:512])\n",
        "word_attributions"
      ]
    },

 %% Cell type:markdown id: tags:
 # BERT Predict classification
 ## 1. Setup the environment
 ### 1.1 Setup colab environment
 #### 1.1.1 Install packages
 %% Cell type:code id: tags:
 ``` python
 !pip install transformers==4.10.3
 !pip install sentencepiece
 !pip install transformers_interpret
 ```
 %% Cell type:markdown id: tags:
 #### 1.1.2 Use more RAM
 %% Cell type:code id: tags:
 ``` python
 from psutil import virtual_memory
 ram_gb = virtual_memory().total / 1e9
 print('Your runtime has {:.1f} gigabytes of available RAM\n'.format(ram_gb))
 if ram_gb < 20:
  print('Not using a high-RAM runtime')
 else:
  print('You are using a high-RAM runtime!')
 ```
 %% Cell type:markdown id: tags:
 #### 1.1.3 Mount GoogleDrive
 %% Cell type:code id: tags:
 ``` python
 from google.colab import drive
 drive.mount('/content/drive')
 ```
 %% Cell type:markdown id: tags:
 ### 1.2 Import librairies
 %% Cell type:code id: tags:
 ``` python
 import pickle
 import torch
 from transformers import BertTokenizer, BertForSequenceClassification
 from transformers_interpret import SequenceClassificationExplainer
 from tqdm import tqdm
 import numpy as np
 import torch
 from torch.utils.data import TensorDataset, DataLoader, SequentialSampler
 import pandas as pd
 ```
 %% Cell type:markdown id: tags:
 ### 1.3 Setup GPU
 %% Cell type:code id: tags:
 ``` python
  # If there's a GPU available...
 if torch.cuda.is_available():
    # Tell PyTorch to use the GPU.
    device = torch.device("cuda")
    gpu_name = "cuda"
    print('There are %d GPU(s) available.' % torch.cuda.device_count())
    print('We will use the GPU:', torch.cuda.get_device_name(0))
 # for MacOS
 elif torch.backends.mps.is_available() and torch.backends.mps.is_built():
    device = torch.device("mps")
    gpu_name = "mps"
    print('We will use the GPU')
 else:
    device = torch.device("cpu")
    gpu_name = "cpu"
    print('No GPU available, using the CPU instead.')
 ```
 %% Output
    We will use the GPU
 %% Cell type:code id: tags:
 ``` python
 device = torch.device("cpu")
 gpu_name = "cpu"
 ```
 %% Cell type:markdown id: tags:
 ## 2. Utils
 %% Cell type:code id: tags:
 ``` python
 def generate_dataloader(tokenizer, sentences, batch_size = 8, max_len = 512):
    # Tokenize all of the sentences and map the tokens to thier word IDs.
    input_ids_test = []
    # For every sentence...
    for sent in sentences:
        # `encode` will:
        #   (1) Tokenize the sentence.
        #   (2) Prepend the `[CLS]` token to the start.
        #   (3) Append the `[SEP]` token to the end.
        #   (4) Map tokens to their IDs.
        encoded_sent = tokenizer.encode(
                            sent,                      # Sentence to encode.
                            add_special_tokens = True, # Add '[CLS]' and '[SEP]'
                            # This function also supports truncation and conversion
                            # to pytorch tensors, but I need to do padding, so I
                            # can't use these features.
                            #max_length = max_len,          # Truncate all sentences.
                            #return_tensors = 'pt',     # Return pytorch tensors.
                    )
        input_ids_test.append(encoded_sent)
    # Pad our input tokens
    padded_test = []
    for i in input_ids_test:
        if len(i) > max_len:
            padded_test.extend([i[:max_len]])
        else:
            padded_test.extend([i + [0] * (max_len - len(i))])
    input_ids_test = np.array(padded_test)
    # Create attention masks
    attention_masks = []
    # Create a mask of 1s for each token followed by 0s for padding
    for seq in input_ids_test:
        seq_mask = [float(i>0) for i in seq]
        attention_masks.append(seq_mask)
    # Convert to tensors.
    inputs = torch.tensor(input_ids_test)
    masks = torch.tensor(attention_masks)
    #set batch size
    # Create the DataLoader.
    data = TensorDataset(inputs, masks)
    prediction_sampler = SequentialSampler(data)
    return DataLoader(data, sampler=prediction_sampler, batch_size=batch_size)
 def predict(model, dataloader, device):
    # Put model in evaluation mode
    model.eval()
    # Tracking variables
    predictions_test , true_labels = [], []
    pred_labels_ = []
    # Predict
    for batch in dataloader:
    # Add batch to GPU
        batch = tuple(t.to(device) for t in batch)
        # Unpack the inputs from the dataloader
        b_input_ids, b_input_mask = batch
        # Telling the model not to compute or store gradients, saving memory and
        # speeding up prediction
        with torch.no_grad():
            # Forward pass, calculate logit predictions
            outputs = model(b_input_ids, token_type_ids=None,
                            attention_mask=b_input_mask)
        logits = outputs[0]
        #print(logits)
        # Move logits and labels to CPU ???
        logits = logits.detach().cpu().numpy()
        #print(logits)
        # Store predictions and true labels
        predictions_test.append(logits)
        pred_labels = []
        for i in range(len(predictions_test)):
            # The predictions for this batch are a 2-column ndarray (one column for "0"
            # and one column for "1"). Pick the label with the highest value and turn this
            # in to a list of 0s and 1s.
            pred_labels_i = np.argmax(predictions_test[i], axis=1).flatten()
            pred_labels.append(pred_labels_i)
    pred_labels_ += [item for sublist in pred_labels for item in sublist]
    return pred_labels_
 ```
 %% Cell type:markdown id: tags:
 ## 3. Load Data
 !! A modifier: charger le corpus parallele : EDdA et LGE
 %% Cell type:markdown id: tags:
 ### 3.1 LGE (Nakala)
 %% Cell type:code id: tags:
 ``` python
 lge_path = "/Users/lmoncla/Nextcloud-LIRIS/GEODE/GEODE - Partage consortium/Corpus/LGE/LGE_dataset_articles.tsv"
 df_LGE = pd.read_csv(lge_path, sep="\t")
 ```
 %% Cell type:code id: tags:
 ``` python
 df_LGE.head()
 ```
 %% Output
                   id tome      filename  \
    0     T1article_1   T1     article_1
    1    T1article_10   T1    article_10
    2   T1article_100   T1   article_100
    3  T1article_1000   T1  article_1000
    4  T1article_1001   T1  article_1001
                                                 content  nb_words
    0          F.-Camille DREYFUS, député de la Seine.\n         6
    1  quimarque un mouvement en avant de l’esprit hu...       212
    2  ABACUS. L’abacus ou abaque était un instrument...      1345
    3  H6SS6)\n1780-1793 Choiseul-Goufficr\n1780-1793...       218
    4                                     1803Le Brun.\n         2
 %% Cell type:code id: tags:
 ``` python
 df_LGE.shape
 ```
 %% Output
    (229475, 5)
 %% Cell type:markdown id: tags:
 ### 3.2 LGE Parallel
 %% Cell type:code id: tags:
 ``` python
 lge_par_path = "/Users/lmoncla/Nextcloud-LIRIS/GEODE/GEODE - Partage consortium/Corpus/LGE/LGE_parallel_dataset_articles.tsv"
 df_LGE_par = pd.read_csv(lge_par_path, sep="\t")
 ```
 %% Cell type:code id: tags:
 ``` python
 df_LGE_par.head()
 ```
 %% Output
                      id tome         filename  \
    0            T1aam-0   T1            aam-0
    1          T1abaco-0   T1          abaco-0
    2         T1abacot-0   T1         abacot-0
    3        T1abaddon-0   T1        abaddon-0
    4  T1abandonnement-0   T1  abandonnement-0
                                                 content  nb_words
    0  AAM. Mesure de capacité pour les liquides en u...        38
    1  ABACO, architecte italien du xvi siècle (V. La...         8
    2  ABACOT. Double couronne que portaient autrefoi...        33
    3  ABADDONou APOLYON le Destructeur. « Elles\nava...       109
    4  ABANDONNEMENT. I. Droit civil. — Ce mot est un...        76
 %% Cell type:markdown id: tags:
 ### 3.3 EDdA (ARTFL)
 %% Cell type:code id: tags:
 ``` python
 edda_path = "/Users/lmoncla/Nextcloud-LIRIS/GEODE/GEODE - Partage consortium/Corpus/EDdA/EDdA_dataset_articles.tsv"
 df_EDdA = pd.read_csv(edda_path, sep="\t")
 ```
 %% Cell type:code id: tags:
 ``` python
 df_EDdA.head()
 ```
 %% Output
       volume  numero                                head                author  \
    0       1       1                          Title Page              unsigned
    1       1       2   A MONSEIGNEUR LE COMTE D'ARGENSON  Diderot & d'Alembert
    2       1       3  DISCOURS PRÉLIMINAIRE DES EDITEURS            d'Alembert
    3       1       5                            A, a & a            Dumarsais5
    4       1       6                                   A            Dumarsais5
         edda_class enccre_id enccre_class  \
    0  unclassified       NaN          NaN
    1  unclassified       NaN          NaN
    2  unclassified       NaN          NaN
    3     Grammaire    v1-1-0    Grammaire
    4  unclassified    v1-1-1    Grammaire
                                                 content  \
    0  \n\nENCYCLOPÉDIE,\nDICTIONNAIRE RAISONNÉ\nDES ...
    1  \n\nA MONSEIGNEUR\nLE COMTE D'ARGENSON,\nMINIS...
    2  \n\nDISCOURS PRÉLIMINAIRE\nDES EDITEURS.\n\n\n...
    3  \nA, a & a s.m. (ordre Encyclopéd.\nEntend. Sc...
    4  \nA, mot, est 1. la troisieme personne du prés...
                               content_without_designant  \
    0  \n\nENCYCLOPÉDIE,\nDICTIONNAIRE RAISONNÉ\nDES ...
    1  \n\nA MONSEIGNEUR\nLE COMTE D'ARGENSON,\nMINIS...
    2  \n\nDISCOURS PRÉLIMINAIRE\nDES EDITEURS.\n\n\n...
    3  \nA, a & a s.m. (ordre Encyclopéd.\nEntend. Sc...
    4  \nA, mot, est 1. la troisieme personne du prés...
                                         first_paragraph  nb_words
    0  \n\nENCYCLOPÉDIE,\nDICTIONNAIRE RAISONNÉ\nDES ...       151
    1  \n\nA MONSEIGNEUR\nLE COMTE D'ARGENSON,\nMINIS...       208
    2       \n\nDISCOURS PRÉLIMINAIRE\nDES EDITEURS.\n\n     44669
    3  \nA, a & a s.m. (ordre Encyclopéd.\nEntend. Sc...       711
    4  \nA, mot, est 1. la troisieme personne du prés...       238
 %% Cell type:markdown id: tags:
 ### 3.4 EDdA Parallel
 %% Cell type:code id: tags:
 ``` python
-edda_par_path = "/Users/lmoncla/Nextcloud-LIRIS/GEODE/GEODE - Partage consortium/Corpus/EDdA/EDdA_dataset_articles.tsv"
+edda_par_path = "/Users/lmoncla/Nextcloud-LIRIS/GEODE/GEODE - Partage consortium/Corpus/EDdA/EDdA_parallel_dataset_articles.tsv"
 df_EDdA_par = pd.read_csv(edda_par_path, sep="\t")
 ```
 %% Cell type:code id: tags:
 ``` python
 df_EDdA_par.head()
 ```
+%% Output
+                  id tome     filename  \
+    0   T1article100   T1   article100
+    1  T1article1016   T1  article1016
+    2  T1article1036   T1  article1036
+    3  T1article1038   T1  article1038
+    4  T1article1039   T1  article1039
+                                                 content  nb_words
+    0  ABATAGE, s. m. On dit dans un chantier & sur\n...        64
+    1  AFFILIATION, s. f. (Jurispr.) s'est dit par le...        69
+    2  AFFLUENT, adj. terme de rivieres, se dit d'une...        50
+    3  AFFORAGE, s. terme de Droit, qui se prend dans...        83
+    4  AFFOUAGE, s. terme de Coûtumes, qui signifie l...        27
 %% Cell type:markdown id: tags:
 ## 4. Load model and predict
 ### 4.1 Load BERT model
 %% Cell type:code id: tags:
 ``` python
 #path = "drive/MyDrive/Classification-EDdA/"
 path = "../"
 model_name = "bert-base-multilingual-cased"
 model_path = path + "models/model_" + model_name + "_s10000.pt"
 ```
 %% Cell type:code id: tags:
 ``` python
 encoder_filename = "models/label_encoder.pkl"
 with open(path + encoder_filename, 'rb') as file:
      encoder = pickle.load(file)
 ```
 %% Cell type:code id: tags:
 ``` python
 tokenizer = BertTokenizer.from_pretrained(model_name)
 ```
 %% Cell type:code id: tags:
 ``` python
 model = BertForSequenceClassification.from_pretrained(model_path).to(gpu_name) #.to("cuda")
 ```
 %% Cell type:markdown id: tags:
 ### 4.2 Prepare datasets
 %% Cell type:code id: tags:
 ``` python
 # LGE
 data_loader_LGE = generate_dataloader(tokenizer, df_LGE.content.values)
 ```
 %% Output
    Token indices sequence length is longer than the specified maximum sequence length for this model (1204 > 512). Running this sequence through the model will result in indexing errors
 %% Cell type:code id: tags:
 ``` python
 # LGE parallel
 data_loader_LGE_par = generate_dataloader(tokenizer, df_LGE_par.content.values)
 ```
 %% Cell type:code id: tags:
 ``` python
 # EDdA
 data_loader_EDdA = generate_dataloader(tokenizer, df_EDdA.content.values)
 ```
 %% Cell type:code id: tags:
 ``` python
 # EDdA parallel
 data_loader_EDdA_par = generate_dataloader(tokenizer, df_EDdA_par.content.values)
 ```
 %% Cell type:markdown id: tags:
 ### 4.3 Predict
 %% Cell type:code id: tags:
 ``` python
 pred_LGE = predict(model, data_loader_LGE, device)
 df_LGE['class_pred'] = list(encoder.inverse_transform(pred_LGE))
 ```
 %% Cell type:code id: tags:
 ``` python
 pred_LGE_par = predict(model, data_loader_LGE_par, device)
 df_LGE_par['class_pred'] = list(encoder.inverse_transform(pred_LGE_par))
 ```
 %% Cell type:code id: tags:
 ``` python
 pred_EDdA = predict(model, data_loader_EDdA, device)
 df_EDdA['class_pred'] = list(encoder.inverse_transform(pred_EDdA))
 ```
 %% Cell type:code id: tags:
 ``` python
 pred_EDdA_par = predict(model, data_loader_EDdA_par, device)
 df_EDdA_par['class_pred'] = list(encoder.inverse_transform(pred_EDdA_par))
 ```
 %% Cell type:code id: tags:
 ``` python
 df_LGE.head()
 ```
 %% Output
                   id tome      filename  \
    0     T1article_1   T1     article_1
    1    T1article_10   T1    article_10
    2   T1article_100   T1   article_100
    3  T1article_1000   T1  article_1000
    4  T1article_1001   T1  article_1001
                                                 content  nb_words
    0          F.-Camille DREYFUS, député de la Seine.\n         6
    1  quimarque un mouvement en avant de l’esprit hu...       212
    2  ABACUS. L’abacus ou abaque était un instrument...      1345
    3  H6SS6)\n1780-1793 Choiseul-Goufficr\n1780-1793...       218
    4                                     1803Le Brun.\n         2
 %% Cell type:markdown id: tags:
 ### 4.4 Save
 %% Cell type:code id: tags:
 ``` python
 filepath = path + "results_LGE/LGE-metadata-withContent.csv"
 df_LGE.to_csv(filepath, sep="\,")
 ```
 %% Cell type:code id: tags:
 ``` python
 df_LGE.drop(columns=['content'], inplace=True)
 filepath = path + "results_LGE/LGE-metadata.csv"
 df_LGE.to_csv(filepath, sep="\,")
 ```
 %% Cell type:markdown id: tags:
 ## 5. BERT XAI
 https://www.kaggle.com/code/rizwanhaidar/deep-learning-xai-models-loading-and-predictions
 %% Cell type:code id: tags:
 ``` python
 cls_explainer = SequenceClassificationExplainer(
    model,
    tokenizer,
    custom_labels=encoder.classes_.tolist()
 )
 ```
 %% Cell type:code id: tags:
 ``` python
 content = df_EDdA.loc[df_EDdA['head']=="LYON"].reset_index().content[0][:512]
 content
 ```
 %% Output
    "\nLYON, (Géogr.) grande, riche, belle, ancienne\n& celebre ville de France, la plus considérable du\nroyaume après Paris, & la capitale du Lyonnois.\nElle se nomme en latin Lugdunum, Lugudunum, Lugdumum Segusianorum, Lugdumum Celtarum, &c.\nVoyez Lugdunum.\n\nLyon fut fondée l'an de Rome 712, quarante-un\nans avant l'ere chrétienne, par Lucius Munatius\nPlancus, qui étoit consul avec AEmilius Lepidus. Il\nla bâtit sur la Sône, au lieu où cette riviere se jette\ndans le Rhône, & il la peupla des citoyens romains \nqui a"
 %% Cell type:code id: tags:
 ``` python
-word_attributions = cls_explainer(content if len(content) < 512 else content[:512])
+word_attributions = cls_explainer(content[:512])
 word_attributions
 ```
 %% Output
    [('[CLS]', 0.0),
     ('L', 0.007399733805079844),
     ('##Y', 0.1456759996705617),
     ('##ON', 0.14307146561933012),
     (',', 0.19909154256915337),
     ('(', 0.09932002907423143),
     ('G', 0.24402357535335403),
     ('##éo', 0.23393328870446992),
     ('##gr', 0.1695800465119405),
     ('.', 0.14162802579543046),
     (')', -0.13544847084394057),
     ('grande', 0.21832893139528123),
     (',', 0.11257940886969105),
     ('riche', 0.07913704700022943),
     (',', 0.05662853362544685),
     ('belle', -0.029909244412604778),
     (',', 0.06873738399629244),
     ('ancienne', 0.12958979621300132),
     ('&', -0.08418116246612357),
     ('celebre', 0.12947489123965564),
     ('ville', 0.478071716663547),
     ('de', 0.03403811335226887),
     ('France', 0.13688799086603975),
     (',', -0.0010714894154601323),
     ('la', -0.006879341345145134),
     ('plus', 0.05840061099213507),
     ('con', 0.026165582559808873),
     ('##sid', 0.03255043778254519),
     ('##érable', 0.05297839086419718),
     ('du', 0.018572791985543135),
     ('royaume', 0.24665610131446675),
     ('après', 0.01785470962170739),
     ('Paris', 0.03310146903416289),
     (',', -0.006856821180122214),
     ('&', -0.006321268573570221),
     ('la', 0.08253583803987206),
     ('capitale', 0.2983988672217172),
     ('du', 0.07376998774114908),
     ('Lyon', 0.04007542253467923),
     ('##noi', 0.02909189419875202),
     ('##s', 0.02625525527522554),
     ('.', 0.0760972913677917),
     ('Elle', 0.0693630173969722),
     ('se', 0.04164162356829115),
     ('nomme', 0.10000471924693329),
     ('en', 0.03010674205624715),
     ('latin', 0.13303588704102381),
     ('Lu', 0.0309274199183622),
     ('##gd', 0.00518317960511743),
     ('##unum', 0.029477331874186236),
     (',', -0.007011581545450849),
     ('Lu', 0.008645628419735481),
     ('##gu', 0.023084632572130535),
     ('##dun', 0.025699022336446258),
     ('##um', 0.03484266276127894),
     (',', 0.0030423079199119554),
     ('Lu', 0.02366442497712222),
     ('##gd', 0.006578965732858923),
     ('##umu', 0.03456580806237662),
     ('##m', 0.026521004509341334),
     ('Se', 0.037503453809376),
     ('##gus', 0.03294045015997047),
     ('##iano', 0.017089445343453365),
     ('##rum', 0.03820084664850618),
     (',', -0.011642202072501788),
     ('Lu', 0.02694302543021504),
     ('##gd', 0.005721331572683938),
     ('##umu', 0.03658546160187376),
     ('##m', 0.03770363967219936),
     ('Cel', 0.014027086848242715),
     ('##tar', 0.025188870477124894),
     ('##um', 0.039922520378568),
     (',', 0.022664305461904344),
     ('&', -0.0494132018474461),
     ('c', 0.0403850871592572),
     ('.', 0.04544699824023643),
     ('Vo', 0.02935262786796574),
     ('##ye', 0.03940461731845493),
     ('##z', 0.029871874749211054),
     ('Lu', 0.026337930390794705),
     ('##gd', -0.00442376201350928),
     ('##unum', 0.025898349689579492),
     ('.', 0.06146632041097513),
     ('Lyon', 0.022692171217471906),
     ('fut', 0.0438798787047486),
     ('fondée', 0.04704211890403151),
     ('l', 0.0451974674122074),
     ("'", 0.06774875716439344),
     ('an', 0.023585319400848195),
     ('de', 0.021013220187771894),
     ('Rome', 0.03688032185991681),
     ('712', 0.054693452829347115),
     (',', 0.007825484996566502),
     ('quarante', 0.028231791558966633),
     ('-', -0.0003846539976056082),
     ('un', 0.03117251985912735),
     ('ans', 0.014472180695321534),
     ('avant', 0.017626577836139475),
     ('l', 0.04620483463390136),
     ("'", 0.05723696778164145),
     ('ere', 0.007590037219544403),
     ('chrétienne', 0.1311835388990743),
     (',', 0.013178253982938232),
     ('par', 0.007011176299182855),
     ('Lucius', 0.0044462351021057325),
     ('Mu', 0.006340399133187405),
     ('##nati', 0.01752347206998558),
     ('##us', 0.015200983089939281),
     ('Plan', 0.030820184404097863),
     ('##cus', 0.01828726599412002),
     (',', -0.008296981653008715),
     ('qui', 0.03778469886529954),
     ('é', 0.024089543382319098),
     ('##toi', 0.01483008688193065),
     ('##t', 0.0036622619849812073),
     ('consul', 0.006312700914285012),
     ('avec', 0.019039309232488966),
     ('AE', -0.010990138859793724),
     ('##mil', 0.02963200210194755),
     ('##ius', -0.00048531039895657175),
     ('Le', 0.016166723086828174),
     ('##pid', 0.01787476167297771),
     ('##us', 0.020667475964218647),
     ('.', 0.029180628239546275),
     ('Il', 0.021736540370470812),
     ('la', 0.03714972247323993),
     ('b', 0.042870227388534604),
     ('##ât', 0.011332787999157318),
     ('##it', 0.009763016011555254),
     ('sur', 0.04260004363332922),
     ('la', 0.04410484491168233),
     ('S', 0.06575101714951456),
     ('##ôn', 0.011241165099203603),
     ('##e', 0.010537012868472688),
     (',', -0.0062768408260973066),
     ('au', -0.0018304190363696647),
     ('lieu', 0.13020947076813982),
     ('où', 0.013157964330803138),
     ('cette', 0.03737564027887762),
     ('rivier', 0.11169096058453537),
     ('##e', 0.04378867745175019),
     ('se', 0.0058271154715995995),
     ('jet', 0.031575857152632385),
     ('##te', 0.020236291895152022),
     ('dans', 0.01852231748257226),
     ('le', 0.03105610182850656),
     ('Rhône', 0.07226400802922804),
     (',', 0.02919256859997905),
     ('&', -0.038176803729996794),
     ('il', 0.00609352197030786),
     ('la', 0.04198219592000479),
     ('peu', 0.040981027718879084),
     ('##pla', 0.005560350755837545),
     ('des', 0.028996120278423045),
     ('citoyens', -0.03278504989463669),
     ('romain', -0.008083189911088765),
     ('##s', 0.01484737615013025),
     ('qui', 0.05804189959646576),
     ('a', -0.022083265525204197),
     ('[SEP]', 0.0)]
 %% Cell type:code id: tags:
 ``` python
 cls_explainer.predicted_class_name
 ```
 %% Output
    'Géographie'
 %% Cell type:code id: tags:
 ``` python
 cls_explainer.visualize()
 ```
 %% Output
    <IPython.core.display.HTML object>
 %% Cell type:code id: tags:
 ``` python
 ```
 %% Cell type:markdown id: tags:
 * récupérer les mots positifs par domaine (EDdA et LGE)
 * faire des nuages de mots et comparer les plus fréquents entre EDdA et LGE (corpus parallèle)
 %% Cell type:markdown id: tags:
 pour chaque domaine
 pour chaque token : moyenne (somme ?) des scores ? ne prendre que les scores au dessus de 0.1 ?
 %% Cell type:code id: tags:
 ``` python
 word_attributions.sort(key=lambda a: a[1], reverse = True)
 word_attributions
 ```
 %% Output
    [('ville', 0.478071716663547),
     ('capitale', 0.2983988672217172),
     ('royaume', 0.24665610131446675),
     ('G', 0.24402357535335403),
     ('##éo', 0.23393328870446992),
     ('grande', 0.21832893139528123),
     (',', 0.19909154256915337),
     ('##gr', 0.1695800465119405),
     ('##Y', 0.1456759996705617),
     ('##ON', 0.14307146561933012),
     ('.', 0.14162802579543046),
     ('France', 0.13688799086603975),
     ('latin', 0.13303588704102381),
     ('chrétienne', 0.1311835388990743),
     ('lieu', 0.13020947076813982),
     ('ancienne', 0.12958979621300132),
     ('celebre', 0.12947489123965564),
     (',', 0.11257940886969105),
     ('rivier', 0.11169096058453537),
     ('nomme', 0.10000471924693329),
     ('(', 0.09932002907423143),
     ('la', 0.08253583803987206),
     ('riche', 0.07913704700022943),
     ('.', 0.0760972913677917),
     ('du', 0.07376998774114908),
     ('Rhône', 0.07226400802922804),
     ('Elle', 0.0693630173969722),
     (',', 0.06873738399629244),
     ("'", 0.06774875716439344),
     ('S', 0.06575101714951456),
     ('.', 0.06146632041097513),
     ('plus', 0.05840061099213507),
     ('qui', 0.05804189959646576),
     ("'", 0.05723696778164145),
     (',', 0.05662853362544685),
     ('712', 0.054693452829347115),
     ('##érable', 0.05297839086419718),
     ('fondée', 0.04704211890403151),
     ('l', 0.04620483463390136),
     ('.', 0.04544699824023643),
     ('l', 0.0451974674122074),
     ('la', 0.04410484491168233),
     ('fut', 0.0438798787047486),
     ('##e', 0.04378867745175019),
     ('b', 0.042870227388534604),
     ('sur', 0.04260004363332922),
     ('la', 0.04198219592000479),
     ('se', 0.04164162356829115),
     ('peu', 0.040981027718879084),
     ('c', 0.0403850871592572),
     ('Lyon', 0.04007542253467923),
     ('##um', 0.039922520378568),
     ('##ye', 0.03940461731845493),
     ('##rum', 0.03820084664850618),
     ('qui', 0.03778469886529954),
     ('##m', 0.03770363967219936),
     ('Se', 0.037503453809376),
     ('cette', 0.03737564027887762),
     ('la', 0.03714972247323993),
     ('Rome', 0.03688032185991681),
     ('##umu', 0.03658546160187376),
     ('##um', 0.03484266276127894),
     ('##umu', 0.03456580806237662),
     ('de', 0.03403811335226887),
     ('Paris', 0.03310146903416289),
     ('##gus', 0.03294045015997047),
     ('##sid', 0.03255043778254519),
     ('jet', 0.031575857152632385),
     ('un', 0.03117251985912735),
     ('le', 0.03105610182850656),
     ('Lu', 0.0309274199183622),
     ('Plan', 0.030820184404097863),
     ('en', 0.03010674205624715),
     ('##z', 0.029871874749211054),
     ('##mil', 0.02963200210194755),
     ('##unum', 0.029477331874186236),
     ('Vo', 0.02935262786796574),
     (',', 0.02919256859997905),
     ('.', 0.029180628239546275),
     ('##noi', 0.02909189419875202),
     ('des', 0.028996120278423045),
     ('quarante', 0.028231791558966633),
     ('Lu', 0.02694302543021504),
     ('##m', 0.026521004509341334),
     ('Lu', 0.026337930390794705),
     ('##s', 0.02625525527522554),
     ('con', 0.026165582559808873),
     ('##unum', 0.025898349689579492),
     ('##dun', 0.025699022336446258),
     ('##tar', 0.025188870477124894),
     ('é', 0.024089543382319098),
     ('Lu', 0.02366442497712222),
     ('an', 0.023585319400848195),
     ('##gu', 0.023084632572130535),
     ('Lyon', 0.022692171217471906),
     (',', 0.022664305461904344),
     ('Il', 0.021736540370470812),
     ('de', 0.021013220187771894),
     ('##us', 0.020667475964218647),
     ('##te', 0.020236291895152022),
     ('avec', 0.019039309232488966),
     ('du', 0.018572791985543135),
     ('dans', 0.01852231748257226),
     ('##cus', 0.01828726599412002),
     ('##pid', 0.01787476167297771),
     ('après', 0.01785470962170739),
     ('avant', 0.017626577836139475),
     ('##nati', 0.01752347206998558),
     ('##iano', 0.017089445343453365),
     ('Le', 0.016166723086828174),
     ('##us', 0.015200983089939281),
     ('##s', 0.01484737615013025),
     ('##toi', 0.01483008688193065),
     ('ans', 0.014472180695321534),
     ('Cel', 0.014027086848242715),
     (',', 0.013178253982938232),
     ('où', 0.013157964330803138),
     ('##ât', 0.011332787999157318),
     ('##ôn', 0.011241165099203603),
     ('##e', 0.010537012868472688),
     ('##it', 0.009763016011555254),
     ('Lu', 0.008645628419735481),
     (',', 0.007825484996566502),
     ('ere', 0.007590037219544403),
     ('L', 0.007399733805079844),
     ('par', 0.007011176299182855),
     ('##gd', 0.006578965732858923),
     ('Mu', 0.006340399133187405),
     ('consul', 0.006312700914285012),
     ('il', 0.00609352197030786),
     ('se', 0.0058271154715995995),
     ('##gd', 0.005721331572683938),
     ('##pla', 0.005560350755837545),
     ('##gd', 0.00518317960511743),
     ('Lucius', 0.0044462351021057325),
     ('##t', 0.0036622619849812073),
     (',', 0.0030423079199119554),
     ('[CLS]', 0.0),
     ('[SEP]', 0.0),
     ('-', -0.0003846539976056082),
     ('##ius', -0.00048531039895657175),
     (',', -0.0010714894154601323),
     ('au', -0.0018304190363696647),
     ('##gd', -0.00442376201350928),
     (',', -0.0062768408260973066),
     ('&', -0.006321268573570221),
     (',', -0.006856821180122214),
     ('la', -0.006879341345145134),
     (',', -0.007011581545450849),
     ('romain', -0.008083189911088765),
     (',', -0.008296981653008715),
     ('AE', -0.010990138859793724),
     (',', -0.011642202072501788),
     ('a', -0.022083265525204197),
     ('belle', -0.029909244412604778),
     ('citoyens', -0.03278504989463669),
     ('&', -0.038176803729996794),
     ('&', -0.0494132018474461),
     ('&', -0.08418116246612357),
     (')', -0.13544847084394057)]
 %% Cell type:code id: tags:
 ``` python
 d = {}
 ```
 %% Cell type:code id: tags:
 ``` python
 d_tmp = dict(word_attributions)
 d_tmp
 ```
 %% Output
    {'ville': 0.478071716663547,
     'capitale': 0.2983988672217172,
     'royaume': 0.24665610131446675,
     'G': 0.24402357535335403,
     '##éo': 0.23393328870446992,
     'grande': 0.21832893139528123,
     ',': -0.011642202072501788,
     '##gr': 0.1695800465119405,
     '##Y': 0.1456759996705617,
     '##ON': 0.14307146561933012,
     '.': 0.029180628239546275,
     'France': 0.13688799086603975,
     'latin': 0.13303588704102381,
     'chrétienne': 0.1311835388990743,
     'lieu': 0.13020947076813982,
     'ancienne': 0.12958979621300132,
     'celebre': 0.12947489123965564,
     'rivier': 0.11169096058453537,
     'nomme': 0.10000471924693329,
     '(': 0.09932002907423143,
     'la': -0.006879341345145134,
     'riche': 0.07913704700022943,
     'du': 0.018572791985543135,
     'Rhône': 0.07226400802922804,
     'Elle': 0.0693630173969722,
     "'": 0.05723696778164145,
     'S': 0.06575101714951456,
     'plus': 0.05840061099213507,
     'qui': 0.03778469886529954,
     '712': 0.054693452829347115,
     '##érable': 0.05297839086419718,
     'fondée': 0.04704211890403151,
     'l': 0.0451974674122074,
     'fut': 0.0438798787047486,
     '##e': 0.010537012868472688,
     'b': 0.042870227388534604,
     'sur': 0.04260004363332922,
     'se': 0.0058271154715995995,
     'peu': 0.040981027718879084,
     'c': 0.0403850871592572,
     'Lyon': 0.022692171217471906,
     '##um': 0.03484266276127894,
     '##ye': 0.03940461731845493,
     '##rum': 0.03820084664850618,
     '##m': 0.026521004509341334,
     'Se': 0.037503453809376,
     'cette': 0.03737564027887762,
     'Rome': 0.03688032185991681,
     '##umu': 0.03456580806237662,
     'de': 0.021013220187771894,
     'Paris': 0.03310146903416289,
     '##gus': 0.03294045015997047,
     '##sid': 0.03255043778254519,
     'jet': 0.031575857152632385,
     'un': 0.03117251985912735,
     'le': 0.03105610182850656,
     'Lu': 0.008645628419735481,
     'Plan': 0.030820184404097863,
     'en': 0.03010674205624715,
     '##z': 0.029871874749211054,
     '##mil': 0.02963200210194755,
     '##unum': 0.025898349689579492,
     'Vo': 0.02935262786796574,
     '##noi': 0.02909189419875202,
     'des': 0.028996120278423045,
     'quarante': 0.028231791558966633,
     '##s': 0.01484737615013025,
     'con': 0.026165582559808873,
     '##dun': 0.025699022336446258,
     '##tar': 0.025188870477124894,
     'é': 0.024089543382319098,
     'an': 0.023585319400848195,
     '##gu': 0.023084632572130535,
     'Il': 0.021736540370470812,
     '##us': 0.015200983089939281,
     '##te': 0.020236291895152022,
     'avec': 0.019039309232488966,
     'dans': 0.01852231748257226,
     '##cus': 0.01828726599412002,
     '##pid': 0.01787476167297771,
     'après': 0.01785470962170739,
     'avant': 0.017626577836139475,
     '##nati': 0.01752347206998558,
     '##iano': 0.017089445343453365,
     'Le': 0.016166723086828174,
     '##toi': 0.01483008688193065,
     'ans': 0.014472180695321534,
     'Cel': 0.014027086848242715,
     'où': 0.013157964330803138,
     '##ât': 0.011332787999157318,
     '##ôn': 0.011241165099203603,
     '##it': 0.009763016011555254,
     'ere': 0.007590037219544403,
     'L': 0.007399733805079844,
     'par': 0.007011176299182855,
     '##gd': -0.00442376201350928,
     'Mu': 0.006340399133187405,
     'consul': 0.006312700914285012,
     'il': 0.00609352197030786,
     '##pla': 0.005560350755837545,
     'Lucius': 0.0044462351021057325,
     '##t': 0.0036622619849812073,
     '[CLS]': 0.0,
     '[SEP]': 0.0,
     '-': -0.0003846539976056082,
     '##ius': -0.00048531039895657175,
     'au': -0.0018304190363696647,
     '&': -0.08418116246612357,
     'romain': -0.008083189911088765,
     'AE': -0.010990138859793724,
     'a': -0.022083265525204197,
     'belle': -0.029909244412604778,
     'citoyens': -0.03278504989463669,
     ')': -0.13544847084394057}
 %% Cell type:code id: tags:
 ``` python
 df_EDdA.enccre_class.unique()
 ```
 %% Output
    array([nan, 'Grammaire', 'Médailles', 'Histoire', 'Caractères',
           'Philosophie', 'Chimie', 'Médecine - Chirurgie', 'Commerce',
           'Géographie', 'Mathématiques', 'Histoire naturelle',
           'Architecture', 'Blason', 'Agriculture - Economie rustique',
           'Chasse', 'Métiers', 'Anatomie', 'Droit - Jurisprudence',
           'Antiquité', 'Marine', 'Militaire (Art) - Guerre - Arme',
           'Economie domestique', 'Maréchage - Manège', 'Jeu', 'Monnaie',
           'Physique - [Sciences physico-mathématiques]', 'Religion', 'Pêche',
           'Pharmacie', 'Musique', 'Beaux-arts', 'Spectacle', 'Politique',
           'Mesure', 'Belles-lettres - Poésie', 'Superstition',
           'Arts et métiers', 'Minéralogie'], dtype=object)
 %% Cell type:code id: tags:
 ``` python
 def get_dict_xai(word_attributions):
    word_attributions.sort(key=lambda a: a[1], reverse = True)
    return dict(word_attributions)
 ```
 %% Cell type:code id: tags:
 ``` python
 df = df_EDdA.copy()
 ```
 %% Cell type:code id: tags:
 ``` python
 df = df.sample(100)
 ```
 %% Cell type:code id: tags:
 ``` python
 d = {}
 # boucle sur les domaines
 for group_name, df_group in df.groupby('enccre_class'):
    d[group_name] = {}
    # boucle sur les articles
    for index, row in tqdm(df_group.iterrows()):
        word_attributions = cls_explainer(row['content'] if len(row['content']) < 512 else row['content'][:512])
        d_tmp = get_dict_xai(word_attributions)
        for k, v in d_tmp.items():
            if k in d[group_name]:
                d[group_name][k] = (d[group_name][k] + v) / 2
            else:
                d[group_name][k] = v
 ```
 %% Output
    2it [00:05,  2.71s/it]
    3it [00:13,  4.63s/it]
    3it [00:10,  3.66s/it]
    2it [00:05,  2.57s/it]
    1it [00:01,  1.19s/it]
    1it [00:02,  2.46s/it]
    1it [00:01,  1.73s/it]
    1it [00:03,  3.13s/it]
    2it [00:09,  4.66s/it]
    11it [00:21,  1.99s/it]
    1it [00:01,  1.41s/it]
    16it [00:47,  2.97s/it]
    2it [00:06,  3.33s/it]
    10it [00:40,  4.09s/it]
    3it [00:06,  2.25s/it]
    1it [00:01,  1.14s/it]
    1it [00:01,  1.60s/it]
    2it [00:06,  3.00s/it]
    1it [00:01,  1.60s/it]
    1it [00:02,  2.46s/it]
    1it [00:00,  1.30it/s]
    4it [00:15,  3.97s/it]
    4it [00:13,  3.41s/it]
    2it [00:07,  3.59s/it]
    1it [00:04,  4.69s/it]
    1it [00:00,  1.24it/s]
 %% Cell type:code id: tags:
 ``` python
 d['Géographie']
 ```
 %% Output
    {'ville': 0.468205314323041,
     'fleuve': 0.2423772411435995,
     'G': 0.23135720218825717,
     ',': 0.0858046931906998,
     'nommée': 0.19227297918896974,
     '##éo': 0.18973738733606565,
     '##GE': 0.16634948535987606,
     '##A': 0.15877744098706795,
     '##gr': 0.16202194372565118,
     '##TI': 0.14030883450630402,
     '.': 0.054787505866608105,
     '##c': 0.0948633585054219,
     '(': 0.0413040601926874,
     'depuis': 0.1051878315897289,
     'nom': 0.18136152655341967,
     'se': 0.08786898558747075,
     '##ce': 0.09317071188401634,
     '##ia': 0.031040617643215574,
     'Allemands': 0.0787047715309721,
     'Ce': 0.06555545762824336,
     'est': 0.074775644174404,
     'romaine': 0.07262679757314543,
     'roi': 0.0716659059875927,
     'Da': 0.0714045742494807,
     '##é': 0.02500576025356923,
     'la': 0.12298598711273313,
     'mais': 0.05591848646995751,
     'T': 0.0541465558097154,
     'Sar': 0.01724425985017986,
     'La': 0.051446794552354624,
     'ensuite': 0.051200901865576555,
     'jet': 0.0829284321696537,
     'J': 0.07546336834323314,
     'république': 0.04943046233577988,
     'ce': 0.057519719498181784,
     'ou': 0.08969930275580645,
     'an': 0.041146473695852476,
     'moderne': 0.04177711856360317,
     '##ché': 0.040774048966399426,
     '##toi': 0.03342140264875253,
     'le': 0.05642199866799782,
     '##ès': 0.11698138135400395,
     '##jana': 0.03818439831225535,
     'les': 0.0757883643580965,
     'Le': 0.03715890519752807,
     '##on': 0.025900328149956048,
     '##a': 0.04319994977377055,
     'Sir': 0.03642712798689307,
     'Tra': 0.030808153025433653,
     'avo': 0.032212276900181,
     'de': 0.06770303542758496,
     '##z': 0.03365499782170345,
     "'": 0.061565814719079584,
     'Ar': 0.032402384389004744,
     'un': 0.03322588462984368,
     'sa': 0.032102001051091615,
     'Hong': 0.03178504105089397,
     '##us': 0.03713196635047464,
     '##bal': 0.03142378925271683,
     '##thus': 0.029706139074928077,
     '##hab': 0.02854877671553812,
     '##rig': 0.028440723473813656,
     '##lp': 0.028348485933541584,
     'D': 0.021142184892655142,
     '##ssent': 0.026560785640090002,
     'ar': 0.02655491286531302,
     '##s': 0.047794961185982546,
     'dont': 0.02121929633019263,
     'dit': 0.018481328341026063,
     '##cus': 0.024522117453619832,
     '##ziu': 0.023636246682512362,
     'celui': 0.023612546696296227,
     'Sam': 0.023408934631155117,
     'd': 0.05567218618641231,
     'dans': 0.10022254602904804,
     '##gent': 0.01748654204829846,
     '##noi': 0.02239494074557525,
     '##ros': 0.021349833073345013,
     'Ist': 0.020901809554305005,
     'con': 0.025748442770215568,
     '##x': 0.02002047701965849,
     'R': 0.030949942486234276,
     'app': 0.018555258608997136,
     '##jano': 0.01808523851267019,
     'Dion': 0.015754758531027112,
     '##zog': 0.014949231310082899,
     'U': 0.014654267300384672,
     'à': 0.08298650083974059,
     '##oe': 0.013082684704750751,
     'sous': -0.0002069181948599748,
     'selon': -0.020082683114963043,
     '##mi': 0.008906287279368003,
     'Cassius': 0.008545442448074718,
     'par': 0.061077180857349866,
     '-': 0.06475762097649433,
     '##t': 0.0048467472813908796,
     '##zet': 0.0063275438230979185,
     '##uy': 0.006086328817223191,
     '##el': 0.0060696145131198575,
     'ca': 0.0056714294799304005,
     '##roi': 0.005468227545142956,
     'trés': 0.002824228104975018,
     '##oit': 0.001711933310961672,
     '##bu': 0.0016690113836018768,
     '[CLS]': 0.0,
     '[SEP]': 0.0,
     'ses': 0.049645402358164066,
     '##ors': -0.0017502978171956062,
     'in': -0.003095317243436783,
     'que': 0.009635328008189985,
     'creu': -0.007475521658293897,
     '&': -0.08000801041182604,
     '##it': 0.0015963173159964771,
     ';': 0.007984840521573309,
     ')': -0.06872271549404119,
     'sentiment': -0.048171146031505886,
     'SAR': -0.07143494474675065,
     'latin': 0.3960803982086443,
     'vallée': 0.24144223688497182,
     'grec': 0.24154434016104503,
     'distingue': 0.20225033977383755,
     'en': 0.026650124208107327,
     '##g': 0.11139228310919369,
     'une': 0.0705267038169397,
     'exemple': 0.02878307063738609,
     'torre': 0.010422364080421317,
     'fonte': 0.07176335280650341,
     'mod': 0.05471099375321398,
     'neige': 0.06716279133677414,
     '##nt': -0.010146726047092878,
     'des': 0.10395928916105898,
     '##al': 0.021472918740770543,
     'l': 0.07719865579756106,
     'toujours': 0.05654656086498567,
     'grandes': 0.0500708177588014,
     '##ns': 0.010472519252392662,
     'h': -0.007529062495164878,
     'aussi': 0.04182030961442956,
     'du': 0.02917787047349929,
     '##rro': 0.041311241708329303,
     '##u': 0.018374918227908328,
     'L': 0.03595023525894895,
     'bien': 0.0283913554226912,
     'autre': 0.057531150082004046,
     'plu': 0.03005047616189665,
     '##ule': 0.0166859230453766,
     'On': 0.008215765462606122,
     '##éra': 0.009599163212087692,
     'qu': 0.021413621005676176,
     '##bre': 0.01200562189665623,
     'terme': 0.02610804943109468,
     '##ima': 0.03813331812513627,
     'E': 0.02353268737063088,
     'é': 0.031069540958438446,
     'n': 0.022605076586881327,
     'puisque': 0.022114351087644566,
     'cela': 0.021728661127459404,
     'on': 0.031637879100526636,
     'ne': 0.023481641713517833,
     '##euse': 0.019031264633545753,
     'souvent': 0.01412861492800689,
     'fort': 0.04442544031371985,
     'danger': 0.013811198066105809,
     'signifie': 0.013575249323296856,
     'après': 0.01941062923428665,
     'met': 0.011327151448637373,
     '##ies': 0.01091580579338499,
     '##que': 0.04353082158018988,
     '##qui': 0.009204343050603915,
     'che': 0.005705843958191305,
     'pour': 0.0021363265380875763,
     '##crit': 0.004866795460923155,
     'co': 0.006828431290704029,
     'pas': 0.006987930951319245,
     '##vo': -0.007773218105616921,
     '##re': 0.015364885611094212,
     '##ure': -0.029633249072781927,
     'tem': -0.03507853370176394,
     'nach': -0.059647272844616725,
     'to': -0.043587086241707595,
     'Torre': -0.07370789174796667,
     'Comme': -0.08102775997694327,
     'lac': 0.2627689961654854,
     'duché': 0.15878063729951344,
     'rivier': 0.1835301313877702,
     'Novo': 0.12531683029473817,
     '##US': 0.0822458506910208,
     'empire': 0.12043364298838244,
     'endroit': 0.12779042183921233,
     'Russie': 0.10463858590067449,
     'sur': 0.04915812925999788,
     '##IA': 0.08076525751909835,
     '##SA': 0.02594775540828238,
     '##gor': 0.08311355621144252,
     '##O': 0.12780809591110026,
     'STAR': 0.037760347726659545,
     'où': 0.05080575319876235,
     'Il': 0.0284042208786913,
     '##e': 0.03364232916886872,
     '##vat': 0.05917044284419409,
     '##n': 0.04476191426913992,
     'Lo': 0.05322826492644412,
     '##te': 0.05775689209126553,
     '##men': 0.025864880430748294,
     '##od': 0.022641329488828195,
     'province': 0.3138687127885894,
     'lieu': 0.288944483446071,
     'septentrional': 0.21736956560941825,
     'bourg': 0.205192644118189,
     '##er': 0.20470878331452866,
     'Amérique': 0.2577046079084956,
     'Frontera': 0.19152877305938218,
     'deux': 0.07898332743727765,
     'Espagne': 0.09686731766445605,
     'Gal': 0.09024113726333705,
     'nouvelle': 0.0828520285184145,
     'Guadalajara': 0.0857800140375107,
     '##ice': 0.06692411701657223,
     '##uat': 0.0508369206389474,
     'X': 0.04064410422404537,
     '##la': 0.028711752575946197,
     '##es': 0.022001482046772214,
     '30': 0.05213470124947088,
     '##ades': -0.01685895398059224,
     'audience': -0.045768989771362824,
     'petite': 0.21919648886046295,
     'royaume': 0.2573068212004148,
     'Naples': 0.23150278005781894,
     '##Z': 0.1830676183440645,
     'Italie': 0.1575315512120412,
     '##J': 0.1573522788542329,
     'terre': 0.08085795705733743,
     '32': 0.12352770141613803,
     '10': 0.07431163055453546,
     'au': 0.034992091061273066,
     'Long': 0.06868800126003936,
     '41': 0.08953747205002806,
     'Labour': 0.07756492814166974,
     'CA': 0.05046508890359498,
     'lat': 0.05319105448357667,
     'Macédoine': 0.3205630652048948,
     '##RI': 0.16460252115303084,
     'partie': 0.15845359313084062,
     'lieux': 0.15247473369694478,
     'habita': 0.13771036963333821,
     '##I': 0.141653889530405,
     'nord': 0.242739838786995,
     '##E': 0.12333498427020301,
     'orientale': 0.12299072447402201,
     'golf': 0.11792822736721131,
     'A': 0.06479200165315122,
     'commun': 0.08994387122081324,
     'voir': 0.08847236372959857,
     '##rma': 0.07365816308437048,
     '##É': 0.07159170704085929,
     '##p': 0.07104594769838767,
     'P': 0.03272049148432894,
     'comme': 0.06549376453090695,
     '##mée': 0.0646449194613384,
     '##ïque': 0.061645981622394784,
     '##én': 0.057367966434507346,
     'Ali': 0.055659756416669474,
     'C': 0.04306076808452276,
     'nomme': 0.05401793892863615,
     'Lu': 0.05137836438835051,
     '##ii': 0.049587268182288424,
     '##olo': 0.04880284359551007,
     'midi': 0.07113877841272949,
     'il': 0.0027654637201536968,
     'va': 0.04337036149864036,
     'Pier': 0.022936152887815472,
     'Pt': 0.04241563924208806,
     '##rab': 0.0423110927679243,
     '##rée': 0.042257144545369996,
     '##iot': 0.04203676192154972,
     'The': 0.04191806043439661,
     'St': 0.04123715089841821,
     'Per': 0.03985223606785319,
     '##j': 0.03926027199963966,
     '##ée': 0.039227260949307896,
     'côté': 0.023297246836922872,
     'cont': 0.03657382982964496,
     '##ae': 0.03185063483930072,
     '##ac': 0.031224938425030026,
     'ex': 0.020417873274345934,
     'différentes': 0.030718941715107615,
     '2°': 0.030522230876155416,
     'VII': 0.02928677630182494,
     '##dia': 0.026233515028085855,
     '##cer': 0.023491982765047097,
     '##xiu': 0.022805612841692573,
     'a': -0.0012715805160076403,
     'commence': 0.014379318563949204,
     '##pt': 0.013195773759531383,
     '##ie': 0.017838742894118582,
     'cha': 0.0067258655884391136,
     'fine': 0.006245003686740857,
     '##mon': 0.002094276853030689,
     '##éir': 0.0059480290294971795,
     'III': 0.00283531432530362,
     'termine': 0.0013832185393301071,
     'x': 0.0008492312750708209,
     'donne': -0.0033814500703101104,
     'liv': -0.01661384524933283,
     'born': -0.041898895862637786,
     '1°': -0.026381150057445416,
     'Asie': 0.25951725852047475,
     'Orient': 0.26844923609680227,
     'Inde': 0.2133903020411604,
     'mer': 0.26868989143550776,
     'desert': 0.15074697961858496,
     'petit': 0.1376690268440502,
     'Cam': 0.12958328223340024,
     '##MP': 0.10974714271316263,
     '##chin': 0.0894472877928192,
     'Co': 0.07783219273122367,
     '##chine': 0.07614065102466291,
     '##bo': 0.06026845472373662,
     'ori': 0.05756818718647703,
     '##cci': 0.05157091008708276,
     '##ge': 0.04400356682753303,
     'o': 0.04070060977171756,
     '##ent': 0.023156820087233715,
     'CIA': 0.020303354874778645,
     '##dent': 0.00517282162953671,
     'capitale': 0.36838594655129425,
     'comté': 0.29220668870626426,
     'milles': 0.18218276737467964,
     'Irlande': 0.17055004990277814,
     'Dublin': 0.14585461747071327,
     'forte': 0.09134790101615797,
     'M': 0.04357113158723378,
     '28': 0.11327727914116813,
     '##AR': 0.0700853626124515,
     '40': 0.10679936658542148,
     'West': 0.08993142493114488,
     '##UL': 0.08819267818570828,
     '12': 0.08319295152975612,
     '##L': 0.13304534043947008,
     '53': 0.08036439319058314,
     'Bat': 0.0781627203933898,
     '13': 0.07480367622434814,
     '##ING': 0.05812388913159779,
     'O': 0.06583622417433492,
     '##éa': 0.05230588344828021,
     '##sh': 0.03433270961563577,
     'MO': 0.030683540302786836,
     '##imo': 0.017082182198960103,
     'let': -0.0461111572568852,
     'remarquable': 0.21263713433629308,
     'qui': 0.050173365888367016,
     'bataille': 0.13091439215231107,
     'Allemagne': 0.11618493617005074,
     'Fu': 0.10846701242333791,
     'entre': 0.06369520587259789,
     '##EN': 0.09069418279503459,
     'fut': 0.08918546414477314,
     '##ER': 0.08840867622071771,
     'mar': 0.08131159281878217,
     '##SH': 0.07880885570732322,
     'Brand': 0.07534765223550378,
     's': 0.07214195178952942,
     'victoire': 0.07404695440084724,
     'Albert': 0.06782766064004295,
     '##êché': 0.06760324837539838,
     '##se': 0.06694410055617671,
     '##we': 0.06692906138119581,
     '##illet': 0.06506627545649421,
     '##grave': 0.06490679816106117,
     '##eb': 0.061676421437111995,
     'Saxe': 0.056318485823556044,
     'blessure': 0.054096736108623616,
     '##fait': 0.05343946030378872,
     'Hildesheim': 0.05099271687488835,
     '##fin': 0.04989368895071508,
     'Maurice': 0.04751196968720714,
     '##ourg': 0.04583679368750848,
     '##lante': 0.03983621993726603,
     '7': 0.03584389050476482,
     'aux': 0.035433950894822305,
     '1553': 0.034349353274837756,
     'dé': 0.03434818892830247,
     'mourut': 0.03360980244865721,
     'év': 0.029168399068651336,
     '##bourg': 0.02789169534010975,
     'plusieurs': 0.02669902130425908,
     'donna': 0.025856769861851345,
     '##ade': 0.023830238910252367,
     'SW': 0.02082288328341326,
     '##ect': 0.020450927253329462,
     'Lune': 0.02024761291388681,
     'él': 0.01741279676584186,
     'jours': 0.016570340432660837,
     'sang': 0.015613060865029399,
     'peu': 0.03996102752601043,
     '##eta': 0.01069390934382476,
     'ach': 0.010388292909415044,
     'Ju': 0.0073498549683621225,
     '##eur': 0.0019017102256399137,
     'y': -0.044396462419225395,
     'Ty': 0.24148741758807102,
     'eaux': 0.21684370603760367,
     'situation': 0.10329824944457552,
     'cité': 0.09052769883978086,
     'Or': 0.019460845999311357,
     '##esti': 0.03883953302868402,
     'Port': -0.1040613277987558,
     'm': 0.05587762491014585,
     'Cal': 0.07697134262504549,
     'appelle': 0.07462975062628824,
     'car': 0.07461062484523039,
     'port': 0.06465359698878792,
     'dire': 0.07059837227461703,
     'cette': 0.08802705291918328,
     '##rr': 0.06022085803296414,
     'sept': 0.057519390301443825,
     '##nien': 0.05355078021839007,
     'fondée': 0.0509239663456544,
     'pur': 0.05064960239352996,
     'assez': 0.05042410659440811,
     'Bari': 0.05030515494264842,
     '##vog': 0.04906152561188761,
     'pré': 0.04549836271489032,
     '##éta': 0.04507297230896154,
     'aujourd': 0.04447144001423532,
     '##ne': 0.0347530163976298,
     '##hé': 0.03961438526125526,
     'ensemble': 0.037956283252757204,
     'hui': 0.03734807021915644,
     'leurs': 0.03687680836802711,
     'être': 0.0343762027708024,
     '##ab': 0.032563279819096465,
     'pou': 0.03124793207062872,
     '##oi': 0.02989229975500687,
     'c': -0.006530315247605613,
     '##uri': 0.026965622143799262,
     'Ra': 0.026882539673090518,
     '##voi': 0.01431455878734083,
     'suivant': 0.02558394558733645,
     '##o': 0.023331497432489353,
     '##i': 0.020948732860884275,
     'soit': 0.020530716687414827,
     '##tend': 0.020495566508082305,
     'loin': 0.019550798182729083,
     '##rie': 0.017169840154727146,
     '##ject': 0.017138782093343834,
     'ora': 0.017038607009944622,
     '##ît': 0.014602155227601584,
     '##êl': 0.014337833594615367,
     '##oso': 0.010042907154746029,
     '##cle': 0.008070864174746364,
     '##este': -0.004142491388013976,
     'Quo': -0.011600711502630034,
     '##ifier': -0.024313910709926605,
     'seul': -0.0305767799476541,
     'accord': -0.0385442098622452,
     'Amazon': 0.268750975733531,
     '##Y': 0.19620519591858654,
     'elle': 0.16664352411683878,
     '##UR': 0.1644776678073895,
     '##AT': 0.15286658491534266,
     '##dion': 0.14541624779420775,
     'Qui': 0.13771435252173025,
     '##éri': 0.06699488014992556,
     '##xos': 0.11031678713869973,
     '##ale': 0.09162023651074921,
     ':': -0.04107125437938059,
     'grande': 0.2745048084212555,
     '##G': 0.1593574100830241,
     '37': 0.15551673881995645,
     '##NI': 0.13384155651705198,
     '56': 0.11739328894256833,
     '51': 0.10404197401916239,
     'Turquie': 0.0990410787816931,
     'Cara': 0.09295436490234411,
     '##manie': 0.08529201860860249,
     'CO': 0.07632048130911342,
     'Portugal': 0.2042976668202922,
     'ruines': 0.20314744837396317,
     'plaine': 0.16178744164448852,
     'située': 0.14874643050344483,
     'sud': 0.11940264716050225,
     'embouchure': 0.11627573925225723,
     'fertile': 0.10563735882960068,
     'ancienne': 0.09576345241389979,
     'été': 0.09014077147035093,
     '##T': 0.07841500408788923,
     '##ob': 0.07632579567509333,
     '##AL': 0.07609846437262502,
     'longueur': 0.061323686830543296,
     'laquelle': 0.06110922821761415,
     '##UB': 0.05967416217649997,
     'b': 0.057586434212371265,
     'mura': 0.054736177441230875,
     'Cet': 0.05395581578984272,
     '##riga': 0.051846567210072046,
     'Za': 0.04995526964949323,
     'plus': 0.04112507132732335,
     '##dao': 0.04753728678912817,
     'S': -0.04602159510840381,
     '##uba': 0.04550942840492348,
     'temple': 0.044018212177904886,
     'pr': 0.04163503255558388,
     'fruits': 0.04113575313188026,
     '##ét': 0.038606207695351155,
     '##ât': 0.03806250021892484,
     'Tage': 0.03765080030853683,
     '##l': 0.036545777864497975,
     'ferme': 0.03580818214260307,
     'soi': 0.040668276790300634,
     'forti': 0.03549622233435284,
     'Lisbon': 0.034290688839724325,
     'Est': 0.034150407829088125,
     'grain': 0.03124989952518535,
     '##r': 0.013680800966903325,
     'vin': 0.030361970705734747,
     '##dou': 0.030107317328042935,
     'fait': 0.024187752198256366,
     '##tr': 0.023949993283441592,
     'Elle': 0.022927855199012262,
     '##ucha': 0.009319170948366045,
     'bout': 0.020885765063577755,
     'vers': 0.020157214084907837,
     'eu': 0.01603845134764128,
     'avant': 0.014469418561726512,
     'Jupiter': 0.01427103838187756,
     'Au': 0.013620171062788134,
     '##fier': 0.006096813392549551,
     'Am': 0.005564187960915995,
     '##ème': 0.004959174323142408,
     '##rama': -0.004348877527747782,
     '##ment': -0.0064917887675220295,
     '##illes': -0.007961146859700573,
     'ouest': 0.286768593993972,
     'villages': 0.20582618265616082,
     'canton': 0.1572237472100742,
     '##UE': 0.13830905321433584,
     '##xi': 0.12866311074641193,
     'quelques': 0.12300477044276094,
     'México': 0.11818705671271108,
     '##EP': 0.08843851847857245,
     '##aca': 0.08293512707914791,
     '##Q': 0.07529631420873374,
     'Pan': 0.06891223037247476,
     '##ho': 0.06749528567182805,
     '##éc': 0.06615958296532198,
     '##fer': 0.06354695452212748,
     '##uco': 0.06345670762758723,
     'ren': 0.05244102948978422,
     '##me': 0.04554978807764583,
     '##OT': 0.03221971618476101,
     'XI': -0.011949950511950972,
     'île': 0.15309594891081557,
     'Java': 0.16105351665895745,
     '##BA': 0.07463413630204671,
     'côte': 0.15127253738509425,
     'TU': 0.05645581765532423,
     'place': 0.11962756867654223,
     '##N': 0.11801784167947217,
     'Ban': 0.08482843899835783,
     'came': 0.08336073380554908,
     'ceinture': 0.06844534842035621,
     'près': 0.07520853958224895,
     '##ON': 0.07452683419741084,
     'haut': 0.04823238398842199,
     '130': 0.04487521666602899,
     'ils': 0.044544039157585216,
     '##tam': 0.04319673648672328,
     'nu': 0.03745403392222305,
     'vont': 0.03470655996970495,
     'toile': 0.03155735621178085,
     'belle': 0.03147662648632047,
     '5': 0.0313537019882558,
     'poi': 0.0294521548866359,
     '##ton': 0.027713782580636243,
     'Ses': 0.024714865988903954,
     '##gnar': 0.018810819002694525,
     'leur': 0.012756004109524549,
     'toute': 0.011917089830431075,
     '##ds': 0.00923735338058978,
     '##d': -0.007455893077793125,
     '##lot': 0.0014408876850427973,
     'tout': -0.003079531645644194,
     'traf': -0.005273322147678258,
     'lati': -0.006057162419608609,
     'portent': -0.010660914154466471,
     '##ique': -0.014304967428463296,
     'Sue': 0.18807178158587753,
     'grand': 0.18657103884394427,
     'sont': 0.09666358953523904,
     '##de': 0.08031207024907842,
     'portée': 0.07505629073993414,
     '##ar': 0.05511323593526249,
     '##lie': 0.05204283271035915,
     'Dal': 0.018382978798721323,
     'SI': -0.0025126387312130413}
 %% Cell type:code id: tags:
 ``` python
 l = [(k, v) for k, v in d['Géographie'].items()]
 l.sort(key=lambda a: a[1], reverse = True)
 l
 ```
 %% Output
    [('ville', 0.468205314323041),
     ('latin', 0.3960803982086443),
     ('capitale', 0.36838594655129425),
     ('Macédoine', 0.3205630652048948),
     ('province', 0.3138687127885894),
     ('comté', 0.29220668870626426),
     ('lieu', 0.288944483446071),
     ('ouest', 0.286768593993972),
     ('grande', 0.2745048084212555),
     ('Amazon', 0.268750975733531),
     ('mer', 0.26868989143550776),
     ('Orient', 0.26844923609680227),
     ('lac', 0.2627689961654854),
     ('Asie', 0.25951725852047475),
     ('Amérique', 0.2577046079084956),
     ('royaume', 0.2573068212004148),
     ('nord', 0.242739838786995),
     ('fleuve', 0.2423772411435995),
     ('grec', 0.24154434016104503),
     ('Ty', 0.24148741758807102),
     ('vallée', 0.24144223688497182),
     ('Naples', 0.23150278005781894),
     ('G', 0.23135720218825717),
     ('petite', 0.21919648886046295),
     ('septentrional', 0.21736956560941825),
     ('eaux', 0.21684370603760367),
     ('Inde', 0.2133903020411604),
     ('remarquable', 0.21263713433629308),
     ('villages', 0.20582618265616082),
     ('bourg', 0.205192644118189),
     ('##er', 0.20470878331452866),
     ('Portugal', 0.2042976668202922),
     ('ruines', 0.20314744837396317),
     ('distingue', 0.20225033977383755),
     ('##Y', 0.19620519591858654),
     ('nommée', 0.19227297918896974),
     ('Frontera', 0.19152877305938218),
     ('##éo', 0.18973738733606565),
     ('Sue', 0.18807178158587753),
     ('grand', 0.18657103884394427),
     ('rivier', 0.1835301313877702),
     ('##Z', 0.1830676183440645),
     ('milles', 0.18218276737467964),
     ('nom', 0.18136152655341967),
     ('Irlande', 0.17055004990277814),
     ('elle', 0.16664352411683878),
     ('##GE', 0.16634948535987606),
     ('##RI', 0.16460252115303084),
     ('##UR', 0.1644776678073895),
     ('##gr', 0.16202194372565118),
     ('plaine', 0.16178744164448852),
     ('Java', 0.16105351665895745),
     ('##G', 0.1593574100830241),
     ('duché', 0.15878063729951344),
     ('##A', 0.15877744098706795),
     ('partie', 0.15845359313084062),
     ('Italie', 0.1575315512120412),
     ('##J', 0.1573522788542329),
     ('canton', 0.1572237472100742),
     ('37', 0.15551673881995645),
     ('île', 0.15309594891081557),
     ('##AT', 0.15286658491534266),
     ('lieux', 0.15247473369694478),
     ('côte', 0.15127253738509425),
     ('desert', 0.15074697961858496),
     ('située', 0.14874643050344483),
     ('Dublin', 0.14585461747071327),
     ('##dion', 0.14541624779420775),
     ('##I', 0.141653889530405),
     ('##TI', 0.14030883450630402),
     ('##UE', 0.13830905321433584),
     ('Qui', 0.13771435252173025),
     ('habita', 0.13771036963333821),
     ('petit', 0.1376690268440502),
     ('##NI', 0.13384155651705198),
     ('##L', 0.13304534043947008),
     ('bataille', 0.13091439215231107),
     ('Cam', 0.12958328223340024),
     ('##xi', 0.12866311074641193),
     ('##O', 0.12780809591110026),
     ('endroit', 0.12779042183921233),
     ('Novo', 0.12531683029473817),
     ('32', 0.12352770141613803),
     ('##E', 0.12333498427020301),
     ('quelques', 0.12300477044276094),
     ('orientale', 0.12299072447402201),
     ('la', 0.12298598711273313),
     ('empire', 0.12043364298838244),
     ('place', 0.11962756867654223),
     ('sud', 0.11940264716050225),
     ('México', 0.11818705671271108),
     ('##N', 0.11801784167947217),
     ('golf', 0.11792822736721131),
     ('56', 0.11739328894256833),
     ('##ès', 0.11698138135400395),
     ('embouchure', 0.11627573925225723),
     ('Allemagne', 0.11618493617005074),
     ('28', 0.11327727914116813),
     ('##g', 0.11139228310919369),
     ('##xos', 0.11031678713869973),
     ('##MP', 0.10974714271316263),
     ('Fu', 0.10846701242333791),
     ('40', 0.10679936658542148),
     ('fertile', 0.10563735882960068),
     ('depuis', 0.1051878315897289),
     ('Russie', 0.10463858590067449),
     ('51', 0.10404197401916239),
     ('des', 0.10395928916105898),
     ('situation', 0.10329824944457552),
     ('dans', 0.10022254602904804),
     ('Turquie', 0.0990410787816931),
     ('Espagne', 0.09686731766445605),
     ('sont', 0.09666358953523904),
     ('ancienne', 0.09576345241389979),
     ('##c', 0.0948633585054219),
     ('##ce', 0.09317071188401634),
     ('Cara', 0.09295436490234411),
     ('##ale', 0.09162023651074921),
     ('forte', 0.09134790101615797),
     ('##EN', 0.09069418279503459),
     ('cité', 0.09052769883978086),
     ('Gal', 0.09024113726333705),
     ('été', 0.09014077147035093),
     ('commun', 0.08994387122081324),
     ('West', 0.08993142493114488),
     ('ou', 0.08969930275580645),
     ('41', 0.08953747205002806),
     ('##chin', 0.0894472877928192),
     ('fut', 0.08918546414477314),
     ('voir', 0.08847236372959857),
     ('##EP', 0.08843851847857245),
     ('##ER', 0.08840867622071771),
     ('##UL', 0.08819267818570828),
     ('cette', 0.08802705291918328),
     ('se', 0.08786898558747075),
     (',', 0.0858046931906998),
     ('Guadalajara', 0.0857800140375107),
     ('##manie', 0.08529201860860249),
     ('Ban', 0.08482843899835783),
     ('came', 0.08336073380554908),
     ('12', 0.08319295152975612),
     ('##gor', 0.08311355621144252),
     ('à', 0.08298650083974059),
     ('##aca', 0.08293512707914791),
     ('jet', 0.0829284321696537),
     ('nouvelle', 0.0828520285184145),
     ('##US', 0.0822458506910208),
     ('mar', 0.08131159281878217),
     ('terre', 0.08085795705733743),
     ('##IA', 0.08076525751909835),
     ('53', 0.08036439319058314),
     ('##de', 0.08031207024907842),
     ('deux', 0.07898332743727765),
     ('##SH', 0.07880885570732322),
     ('Allemands', 0.0787047715309721),
     ('##T', 0.07841500408788923),
     ('Bat', 0.0781627203933898),
     ('Co', 0.07783219273122367),
     ('Labour', 0.07756492814166974),
     ('l', 0.07719865579756106),
     ('Cal', 0.07697134262504549),
     ('##ob', 0.07632579567509333),
     ('CO', 0.07632048130911342),
     ('##chine', 0.07614065102466291),
     ('##AL', 0.07609846437262502),
     ('les', 0.0757883643580965),
     ('J', 0.07546336834323314),
     ('Brand', 0.07534765223550378),
     ('##Q', 0.07529631420873374),
     ('près', 0.07520853958224895),
     ('portée', 0.07505629073993414),
     ('13', 0.07480367622434814),
     ('est', 0.074775644174404),
     ('##BA', 0.07463413630204671),
     ('appelle', 0.07462975062628824),
     ('car', 0.07461062484523039),
     ('##ON', 0.07452683419741084),
     ('10', 0.07431163055453546),
     ('victoire', 0.07404695440084724),
     ('##rma', 0.07365816308437048),
     ('romaine', 0.07262679757314543),
     ('s', 0.07214195178952942),
     ('fonte', 0.07176335280650341),
     ('roi', 0.0716659059875927),
     ('##É', 0.07159170704085929),
     ('Da', 0.0714045742494807),
     ('midi', 0.07113877841272949),
     ('##p', 0.07104594769838767),
     ('dire', 0.07059837227461703),
     ('une', 0.0705267038169397),
     ('##AR', 0.0700853626124515),
     ('Pan', 0.06891223037247476),
     ('Long', 0.06868800126003936),
     ('ceinture', 0.06844534842035621),
     ('Albert', 0.06782766064004295),
     ('de', 0.06770303542758496),
     ('##êché', 0.06760324837539838),
     ('##ho', 0.06749528567182805),
     ('neige', 0.06716279133677414),
     ('##éri', 0.06699488014992556),
     ('##se', 0.06694410055617671),
     ('##we', 0.06692906138119581),
     ('##ice', 0.06692411701657223),
     ('##éc', 0.06615958296532198),
     ('O', 0.06583622417433492),
     ('Ce', 0.06555545762824336),
     ('comme', 0.06549376453090695),
     ('##illet', 0.06506627545649421),
     ('##grave', 0.06490679816106117),
     ('A', 0.06479200165315122),
     ('-', 0.06475762097649433),
     ('port', 0.06465359698878792),
     ('##mée', 0.0646449194613384),
     ('entre', 0.06369520587259789),
     ('##fer', 0.06354695452212748),
     ('##uco', 0.06345670762758723),
     ('##eb', 0.061676421437111995),
     ('##ïque', 0.061645981622394784),
     ("'", 0.061565814719079584),
     ('longueur', 0.061323686830543296),
     ('laquelle', 0.06110922821761415),
     ('par', 0.061077180857349866),
     ('##bo', 0.06026845472373662),
     ('##rr', 0.06022085803296414),
     ('##UB', 0.05967416217649997),
     ('##vat', 0.05917044284419409),
     ('##ING', 0.05812388913159779),
     ('##te', 0.05775689209126553),
     ('b', 0.057586434212371265),
     ('ori', 0.05756818718647703),
     ('autre', 0.057531150082004046),
     ('ce', 0.057519719498181784),
     ('sept', 0.057519390301443825),
     ('##én', 0.057367966434507346),
     ('toujours', 0.05654656086498567),
     ('TU', 0.05645581765532423),
     ('le', 0.05642199866799782),
     ('Saxe', 0.056318485823556044),
     ('mais', 0.05591848646995751),
     ('m', 0.05587762491014585),
     ('d', 0.05567218618641231),
     ('Ali', 0.055659756416669474),
     ('##ar', 0.05511323593526249),
     ('.', 0.054787505866608105),
     ('mura', 0.054736177441230875),
     ('mod', 0.05471099375321398),
     ('T', 0.0541465558097154),
     ('blessure', 0.054096736108623616),
     ('nomme', 0.05401793892863615),
     ('Cet', 0.05395581578984272),
     ('##nien', 0.05355078021839007),
     ('##fait', 0.05343946030378872),
     ('Lo', 0.05322826492644412),
     ('lat', 0.05319105448357667),
     ('ren', 0.05244102948978422),
     ('##éa', 0.05230588344828021),
     ('30', 0.05213470124947088),
     ('##lie', 0.05204283271035915),
     ('##riga', 0.051846567210072046),
     ('##cci', 0.05157091008708276),
     ('La', 0.051446794552354624),
     ('Lu', 0.05137836438835051),
     ('ensuite', 0.051200901865576555),
     ('Hildesheim', 0.05099271687488835),
     ('fondée', 0.0509239663456544),
     ('##uat', 0.0508369206389474),
     ('où', 0.05080575319876235),
     ('pur', 0.05064960239352996),
     ('CA', 0.05046508890359498),
     ('assez', 0.05042410659440811),
     ('Bari', 0.05030515494264842),
     ('qui', 0.050173365888367016),
     ('grandes', 0.0500708177588014),
     ('Za', 0.04995526964949323),
     ('##fin', 0.04989368895071508),
     ('ses', 0.049645402358164066),
     ('##ii', 0.049587268182288424),
     ('république', 0.04943046233577988),
     ('sur', 0.04915812925999788),
     ('##vog', 0.04906152561188761),
     ('##olo', 0.04880284359551007),
     ('haut', 0.04823238398842199),
     ('##s', 0.047794961185982546),
     ('##dao', 0.04753728678912817),
     ('Maurice', 0.04751196968720714),
     ('##ourg', 0.04583679368750848),
     ('##me', 0.04554978807764583),
     ('##uba', 0.04550942840492348),
     ('pré', 0.04549836271489032),
     ('##éta', 0.04507297230896154),
     ('130', 0.04487521666602899),
     ('##n', 0.04476191426913992),
     ('ils', 0.044544039157585216),
     ('aujourd', 0.04447144001423532),
     ('fort', 0.04442544031371985),
     ('temple', 0.044018212177904886),
     ('##ge', 0.04400356682753303),
     ('M', 0.04357113158723378),
     ('##que', 0.04353082158018988),
     ('va', 0.04337036149864036),
     ('##a', 0.04319994977377055),
     ('##tam', 0.04319673648672328),
     ('C', 0.04306076808452276),
     ('Pt', 0.04241563924208806),
     ('##rab', 0.0423110927679243),
     ('##rée', 0.042257144545369996),
     ('##iot', 0.04203676192154972),
     ('The', 0.04191806043439661),
     ('aussi', 0.04182030961442956),
     ('moderne', 0.04177711856360317),
     ('pr', 0.04163503255558388),
     ('##rro', 0.041311241708329303),
     ('(', 0.0413040601926874),
     ('St', 0.04123715089841821),
     ('an', 0.041146473695852476),
     ('fruits', 0.04113575313188026),
     ('plus', 0.04112507132732335),
     ('##ché', 0.040774048966399426),
     ('o', 0.04070060977171756),
     ('soi', 0.040668276790300634),
     ('X', 0.04064410422404537),
     ('peu', 0.03996102752601043),
     ('Per', 0.03985223606785319),
     ('##lante', 0.03983621993726603),
     ('##hé', 0.03961438526125526),
     ('##j', 0.03926027199963966),
     ('##ée', 0.039227260949307896),
     ('##esti', 0.03883953302868402),
     ('##ét', 0.038606207695351155),
     ('##jana', 0.03818439831225535),
     ('##ima', 0.03813331812513627),
     ('##ât', 0.03806250021892484),
     ('ensemble', 0.037956283252757204),
     ('STAR', 0.037760347726659545),
     ('Tage', 0.03765080030853683),
     ('nu', 0.03745403392222305),
     ('hui', 0.03734807021915644),
     ('Le', 0.03715890519752807),
     ('##us', 0.03713196635047464),
     ('leurs', 0.03687680836802711),
     ('cont', 0.03657382982964496),
     ('##l', 0.036545777864497975),
     ('Sir', 0.03642712798689307),
     ('L', 0.03595023525894895),
     ('7', 0.03584389050476482),
     ('ferme', 0.03580818214260307),
     ('forti', 0.03549622233435284),
     ('aux', 0.035433950894822305),
     ('au', 0.034992091061273066),
     ('##ne', 0.0347530163976298),
     ('vont', 0.03470655996970495),
     ('être', 0.0343762027708024),
     ('1553', 0.034349353274837756),
     ('dé', 0.03434818892830247),
     ('##sh', 0.03433270961563577),
     ('Lisbon', 0.034290688839724325),
     ('Est', 0.034150407829088125),
     ('##z', 0.03365499782170345),
     ('##e', 0.03364232916886872),
     ('mourut', 0.03360980244865721),
     ('##toi', 0.03342140264875253),
     ('un', 0.03322588462984368),
     ('P', 0.03272049148432894),
     ('##ab', 0.032563279819096465),
     ('Ar', 0.032402384389004744),
     ('##OT', 0.03221971618476101),
     ('avo', 0.032212276900181),
     ('sa', 0.032102001051091615),
     ('##ae', 0.03185063483930072),
     ('Hong', 0.03178504105089397),
     ('on', 0.031637879100526636),
     ('toile', 0.03155735621178085),
     ('belle', 0.03147662648632047),
     ('##bal', 0.03142378925271683),
     ('5', 0.0313537019882558),
     ('grain', 0.03124989952518535),
     ('pou', 0.03124793207062872),
     ('##ac', 0.031224938425030026),
     ('é', 0.031069540958438446),
     ('##ia', 0.031040617643215574),
     ('R', 0.030949942486234276),
     ('Tra', 0.030808153025433653),
     ('différentes', 0.030718941715107615),
     ('MO', 0.030683540302786836),
     ('2°', 0.030522230876155416),
     ('vin', 0.030361970705734747),
     ('##dou', 0.030107317328042935),
     ('plu', 0.03005047616189665),
     ('##oi', 0.02989229975500687),
     ('##thus', 0.029706139074928077),
     ('poi', 0.0294521548866359),
     ('VII', 0.02928677630182494),
     ('du', 0.02917787047349929),
     ('év', 0.029168399068651336),
     ('exemple', 0.02878307063738609),
     ('##la', 0.028711752575946197),
     ('##hab', 0.02854877671553812),
     ('##rig', 0.028440723473813656),
     ('Il', 0.0284042208786913),
     ('bien', 0.0283913554226912),
     ('##lp', 0.028348485933541584),
     ('##bourg', 0.02789169534010975),
     ('##ton', 0.027713782580636243),
     ('##uri', 0.026965622143799262),
     ('Ra', 0.026882539673090518),
     ('plusieurs', 0.02669902130425908),
     ('en', 0.026650124208107327),
     ('##ssent', 0.026560785640090002),
     ('ar', 0.02655491286531302),
     ('##dia', 0.026233515028085855),
     ('terme', 0.02610804943109468),
     ('##SA', 0.02594775540828238),
     ('##on', 0.025900328149956048),
     ('##men', 0.025864880430748294),
     ('donna', 0.025856769861851345),
     ('con', 0.025748442770215568),
     ('suivant', 0.02558394558733645),
     ('##é', 0.02500576025356923),
     ('Ses', 0.024714865988903954),
     ('##cus', 0.024522117453619832),
     ('fait', 0.024187752198256366),
     ('##tr', 0.023949993283441592),
     ('##ade', 0.023830238910252367),
     ('##ziu', 0.023636246682512362),
     ('celui', 0.023612546696296227),
     ('E', 0.02353268737063088),
     ('##cer', 0.023491982765047097),
     ('ne', 0.023481641713517833),
     ('Sam', 0.023408934631155117),
     ('##o', 0.023331497432489353),
     ('côté', 0.023297246836922872),
     ('##ent', 0.023156820087233715),
     ('Pier', 0.022936152887815472),
     ('Elle', 0.022927855199012262),
     ('##xiu', 0.022805612841692573),
     ('##od', 0.022641329488828195),
     ('n', 0.022605076586881327),
     ('##noi', 0.02239494074557525),
     ('puisque', 0.022114351087644566),
     ('##es', 0.022001482046772214),
     ('cela', 0.021728661127459404),
     ('##al', 0.021472918740770543),
     ('qu', 0.021413621005676176),
     ('##ros', 0.021349833073345013),
     ('dont', 0.02121929633019263),
     ('D', 0.021142184892655142),
     ('##i', 0.020948732860884275),
     ('Ist', 0.020901809554305005),
     ('bout', 0.020885765063577755),
     ('SW', 0.02082288328341326),
     ('soit', 0.020530716687414827),
     ('##tend', 0.020495566508082305),
     ('##ect', 0.020450927253329462),
     ('ex', 0.020417873274345934),
     ('CIA', 0.020303354874778645),
     ('Lune', 0.02024761291388681),
     ('vers', 0.020157214084907837),
     ('##x', 0.02002047701965849),
     ('loin', 0.019550798182729083),
     ('Or', 0.019460845999311357),
     ('après', 0.01941062923428665),
     ('##euse', 0.019031264633545753),
     ('##gnar', 0.018810819002694525),
     ('app', 0.018555258608997136),
     ('dit', 0.018481328341026063),
     ('Dal', 0.018382978798721323),
     ('##u', 0.018374918227908328),
     ('##jano', 0.01808523851267019),
     ('##ie', 0.017838742894118582),
     ('##gent', 0.01748654204829846),
     ('él', 0.01741279676584186),
     ('Sar', 0.01724425985017986),
     ('##rie', 0.017169840154727146),
     ('##ject', 0.017138782093343834),
     ('##imo', 0.017082182198960103),
     ('ora', 0.017038607009944622),
     ('##ule', 0.0166859230453766),
     ('jours', 0.016570340432660837),
     ('eu', 0.01603845134764128),
     ('Dion', 0.015754758531027112),
     ('sang', 0.015613060865029399),
     ('##re', 0.015364885611094212),
     ('##zog', 0.014949231310082899),
     ('U', 0.014654267300384672),
     ('##ît', 0.014602155227601584),
     ('avant', 0.014469418561726512),
     ('commence', 0.014379318563949204),
     ('##êl', 0.014337833594615367),
     ('##voi', 0.01431455878734083),
     ('Jupiter', 0.01427103838187756),
     ('souvent', 0.01412861492800689),
     ('danger', 0.013811198066105809),
     ('##r', 0.013680800966903325),
     ('Au', 0.013620171062788134),
     ('signifie', 0.013575249323296856),
     ('##pt', 0.013195773759531383),
     ('##oe', 0.013082684704750751),
     ('leur', 0.012756004109524549),
     ('##bre', 0.01200562189665623),
     ('toute', 0.011917089830431075),
     ('met', 0.011327151448637373),
     ('##ies', 0.01091580579338499),
     ('##eta', 0.01069390934382476),
     ('##ns', 0.010472519252392662),
     ('torre', 0.010422364080421317),
     ('ach', 0.010388292909415044),
     ('##oso', 0.010042907154746029),
     ('que', 0.009635328008189985),
     ('##éra', 0.009599163212087692),
     ('##ucha', 0.009319170948366045),
     ('##ds', 0.00923735338058978),
     ('##qui', 0.009204343050603915),
     ('##mi', 0.008906287279368003),
     ('Cassius', 0.008545442448074718),
     ('On', 0.008215765462606122),
     ('##cle', 0.008070864174746364),
     (';', 0.007984840521573309),
     ('Ju', 0.0073498549683621225),
     ('pas', 0.006987930951319245),
     ('co', 0.006828431290704029),
     ('cha', 0.0067258655884391136),
     ('##zet', 0.0063275438230979185),
     ('fine', 0.006245003686740857),
     ('##fier', 0.006096813392549551),
     ('##uy', 0.006086328817223191),
     ('##el', 0.0060696145131198575),
     ('##éir', 0.0059480290294971795),
     ('che', 0.005705843958191305),
     ('ca', 0.0056714294799304005),
     ('Am', 0.005564187960915995),
     ('##roi', 0.005468227545142956),
     ('##dent', 0.00517282162953671),
     ('##ème', 0.004959174323142408),
     ('##crit', 0.004866795460923155),
     ('##t', 0.0048467472813908796),
     ('III', 0.00283531432530362),
     ('trés', 0.002824228104975018),
     ('il', 0.0027654637201536968),
     ('pour', 0.0021363265380875763),
     ('##mon', 0.002094276853030689),
     ('##eur', 0.0019017102256399137),
     ('##oit', 0.001711933310961672),
     ('##bu', 0.0016690113836018768),
     ('##it', 0.0015963173159964771),
     ('##lot', 0.0014408876850427973),
     ('termine', 0.0013832185393301071),
     ('x', 0.0008492312750708209),
     ('[CLS]', 0.0),
     ('[SEP]', 0.0),
     ('sous', -0.0002069181948599748),
     ('a', -0.0012715805160076403),
     ('##ors', -0.0017502978171956062),
     ('SI', -0.0025126387312130413),
     ('tout', -0.003079531645644194),
     ('in', -0.003095317243436783),
     ('donne', -0.0033814500703101104),
     ('##este', -0.004142491388013976),
     ('##rama', -0.004348877527747782),
     ('traf', -0.005273322147678258),
     ('lati', -0.006057162419608609),
     ('##ment', -0.0064917887675220295),
     ('c', -0.006530315247605613),
     ('##d', -0.007455893077793125),
     ('creu', -0.007475521658293897),
     ('h', -0.007529062495164878),
     ('##vo', -0.007773218105616921),
     ('##illes', -0.007961146859700573),
     ('##nt', -0.010146726047092878),
     ('portent', -0.010660914154466471),
     ('Quo', -0.011600711502630034),
     ('XI', -0.011949950511950972),
     ('##ique', -0.014304967428463296),
     ('liv', -0.01661384524933283),
     ('##ades', -0.01685895398059224),
     ('selon', -0.020082683114963043),
     ('##ifier', -0.024313910709926605),
     ('1°', -0.026381150057445416),
     ('##ure', -0.029633249072781927),
     ('seul', -0.0305767799476541),
     ('tem', -0.03507853370176394),
     ('accord', -0.0385442098622452),
     (':', -0.04107125437938059),
     ('born', -0.041898895862637786),
     ('to', -0.043587086241707595),
     ('y', -0.044396462419225395),
     ('audience', -0.045768989771362824),
     ('S', -0.04602159510840381),
     ('let', -0.0461111572568852),
     ('sentiment', -0.048171146031505886),
     ('nach', -0.059647272844616725),
     (')', -0.06872271549404119),
     ('SAR', -0.07143494474675065),
     ('Torre', -0.07370789174796667),
     ('&', -0.08000801041182604),
     ('Comme', -0.08102775997694327),
     ('Port', -0.1040613277987558)]
 %% Cell type:code id: tags:
 ``` python
 l = [(k, v) for k, v in d['Histoire'].items()]
 l.sort(key=lambda a: a[1], reverse = True)
 l
 ```
 %% Output
    [('m', 0.40633566091131035),
     ('nom', 0.3458214847350235),
     ('historiens', 0.30862924390515073),
     ('s', 0.3077777094666005),
     ('Angleterre', 0.2337920536519143),
     ('##ient', 0.19580712386703672),
     ('comté', 0.14833858844766837),
     ('second', 0.14820616290018154),
     ('pl', 0.1463281902011242),
     ('poste', 0.14323795796283648),
     ('Hist', 0.14218800778526514),
     ('##ito', 0.13969328688970806),
     ('##sita', 0.1280014345411447),
     ('hab', 0.11652014547079982),
     ('comme', 0.11188170814742139),
     ('anciens', 0.11027232859611118),
     ('##usi', 0.10947085362788891),
     ('nos', 0.10762903275291207),
     ('##X', 0.1005805525354637),
     ('##c', 0.10015186438256996),
     ('an', 0.09648203036131225),
     ('affect', 0.09530701819855351),
     ('vient', 0.09334766704470135),
     ('##E', 0.09274172459154978),
     ('occupa', 0.08942963262827937),
     ('And', 0.08824648677383519),
     ('l', 0.0831444108231522),
     ('créé', 0.08306820589587903),
     ('Il', 0.0802525747513547),
     ('##alo', 0.07944165678487682),
     ('fils', 0.07878572633572721),
     ('##crive', 0.07730113556902),
     ('f', 0.07687161513015221),
     ('duché', 0.07152755021320736),
     ('##UL', 0.068920897640158),
     ('##U', 0.06701168109866709),
     ('##TA', 0.06379073714776834),
     ('partie', 0.06336604967850502),
     ('une', 0.06293001400537444),
     ('la', 0.0626827034395569),
     ('##NI', 0.06060879691257725),
     ('duc', 0.060449964135058896),
     ('Portugal', 0.05976240345910968),
     ('##S', 0.057922495862996685),
     ('armes', 0.05763547000153224),
     ('##É', 0.057597313355056134),
     ('premier', 0.05650131136433099),
     ('roi', 0.05595339444458686),
     ("'", 0.054559329877048986),
     ('Romains', 0.05104433937584386),
     ('##CI', 0.04991247745965172),
     ('dans', 0.04683541514897137),
     ('posse', 0.04601685231132299),
     ('##étique', 0.04578876328373981),
     ('fut', 0.04558935519068275),
     ('tem', 0.04553165486762242),
     ('mod', 0.04336368647999369),
     ('sa', 0.04312663582043505),
     ('##ond', 0.040984157917012765),
     ('avo', 0.04051199330086981),
     ('femme', 0.03757626958787695),
     ('Clare', 0.036022498192356825),
     (')', 0.035690660988266225),
     ('c', 0.035580215549090806),
     ('trois', 0.03534531063748135),
     ('##e', 0.0350972190161163),
     ('terre', 0.03289370991419495),
     ('é', 0.03272807035735632),
     ('François', 0.03239359465926122),
     ('Espagne', 0.032368113353630164),
     ('devenu', 0.03229911266839503),
     ('Vo', 0.03188328560089204),
     ('##EN', 0.031208214635954697),
     ('III', 0.030991483761359837),
     ('h', 0.030069242575632493),
     ('Roi', 0.030003469570913023),
     ('##ye', 0.02903003695461631),
     ('à', 0.028589994974646694),
     ('Clarence', 0.028489464477414392),
     ('IV', 0.028143981425416645),
     ('##nie', 0.02768313810342139),
     ('étant', 0.026340927727638207),
     ('##sse', 0.026016168412132286),
     ('##it', 0.022331074154075873),
     ('de', 0.021088133952241003),
     ('Edouard', 0.020242216027167314),
     ('(', 0.019469240875565032),
     ('un', 0.01930394072485968),
     ('##IE', 0.018411360404024364),
     ('Thom', 0.017349739492096148),
     ('ce', 0.01719950485751714),
     ('##ur', 0.016483046513021214),
     ('##nt', 0.016016739337704203),
     ('##chu', 0.015601898501551158),
     ('lui', 0.014232570873439493),
     ('d', 0.012780386271698287),
     ('app', 0.012536523456252611),
     ('##s', 0.011660356091300485),
     ('Ce', 0.010793171581974913),
     ('le', 0.010778818997477383),
     ('##ée', 0.009759282079499483),
     ('##oit', 0.008672358830146106),
     ('##arten', 0.008646284725542878),
     ('il', 0.005702086021636536),
     ('##NS', 0.005693935541883908),
     ('en', 0.0043551674016225304),
     ('##éra', 0.004037004014395021),
     ('##ort', 0.003902753055284708),
     ('##CE', 0.0003593292110211764),
     ('[CLS]', 0.0),
     ('[SEP]', 0.0),
     ('##ut', -9.915939616175563e-05),
     ('##réa', -0.0010687617835396714),
     ('##ieme', -0.007155774598079843),
     ('##z', -0.008830385943257218),
     ('au', -0.010348566917927805),
     ('Lionel', -0.013749864105647325),
     ('##é', -0.015446660519507572),
     ('Lu', -0.020325085739928896),
     ('que', -0.020383708539975235),
     ('TU', -0.021388873125663347),
     ('-', -0.025802582476853374),
     ('des', -0.027998968502838124),
     ('##AR', -0.029229992016931022),
     ('B', -0.029730676972465106),
     ('##RD', -0.030606004670801854),
     ('du', -0.04385291573716607),
     ('.', -0.04457615506556049),
     ('no', -0.047490509302559034),
     ('ou', -0.04832152919030737),
     ('qui', -0.05547125005789886),
     ('CL', -0.07023955246241759),
     (',', -0.07295463363450089),
     ('peuples', -0.15972786319846213),
     ('mariage', -0.2230970846131238),
     ('&', -0.2716457925014497)]
 %% Cell type:code id: tags:
 ``` python
 ```