Bump version

ThilinaRajapakse · Dec 18, 2023 · 5219fe7 · 5219fe7
1 parent 76d9801
commit 5219fe7
Show file tree

Hide file tree

Showing 27 changed files with 176 additions and 126 deletions.
diff --git a/examples/t5/mixed_tasks/data_prep.ipynb b/examples/t5/mixed_tasks/data_prep.ipynb
@@ -52,30 +52,34 @@
     }
    ],
    "source": [
-    "prefix = 'data/binary_classification/'\n",
+    "prefix = \"data/binary_classification/\"\n",
     "\n",
-    "binary_train_df = pd.read_csv(prefix + 'train.csv', header=None)\n",
+    "binary_train_df = pd.read_csv(prefix + \"train.csv\", header=None)\n",
     "binary_train_df.head()\n",
     "\n",
-    "binary_eval_df = pd.read_csv(prefix + 'test.csv', header=None)\n",
+    "binary_eval_df = pd.read_csv(prefix + \"test.csv\", header=None)\n",
     "binary_eval_df.head()\n",
     "\n",
     "binary_train_df[0] = (binary_train_df[0] == 2).astype(int)\n",
     "binary_eval_df[0] = (binary_eval_df[0] == 2).astype(int)\n",
     "\n",
-    "binary_train_df = pd.DataFrame({\n",
-    "    'prefix': [\"binary classification\" for i in range(len(binary_train_df))],\n",
-    "    'input_text': binary_train_df[1].str.replace('\\n', ' '),\n",
-    "    'target_text': binary_train_df[0].astype(str),\n",
-    "})\n",
+    "binary_train_df = pd.DataFrame(\n",
+    "    {\n",
+    "        \"prefix\": [\"binary classification\" for i in range(len(binary_train_df))],\n",
+    "        \"input_text\": binary_train_df[1].str.replace(\"\\n\", \" \"),\n",
+    "        \"target_text\": binary_train_df[0].astype(str),\n",
+    "    }\n",
+    ")\n",
     "\n",
     "print(binary_train_df.head())\n",
     "\n",
-    "binary_eval_df = pd.DataFrame({\n",
-    "    'prefix': [\"binary classification\" for i in range(len(binary_eval_df))],\n",
-    "    'input_text': binary_eval_df[1].str.replace('\\n', ' '),\n",
-    "    'target_text': binary_eval_df[0].astype(str),\n",
-    "})\n",
+    "binary_eval_df = pd.DataFrame(\n",
+    "    {\n",
+    "        \"prefix\": [\"binary classification\" for i in range(len(binary_eval_df))],\n",
+    "        \"input_text\": binary_eval_df[1].str.replace(\"\\n\", \" \"),\n",
+    "        \"target_text\": binary_eval_df[0].astype(str),\n",
+    "    }\n",
+    ")\n",
     "\n",
     "\n",
     "print(binary_eval_df.head())"
@@ -171,16 +175,29 @@
    "source": [
     "prefix = \"data/multilabel_classification/\"\n",
     "\n",
-    "multi_train_df = pd.read_csv(prefix + 'train.csv')\n",
-    "multi_train_df[\"comment_text\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
+    "multi_train_df = pd.read_csv(prefix + \"train.csv\")\n",
+    "multi_train_df[\"comment_text\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
     "\n",
     "for col in multi_train_df.columns:\n",
     "    if col not in [\"id\", \"comment_text\"]:\n",
     "        multi_train_df[col] = multi_train_df[col].apply(lambda x: col if x else \"\")\n",
     "\n",
-    "multi_train_df[\"target_text\"] = multi_train_df['toxic'].str.cat(multi_train_df[[col for col in multi_train_df.columns if col not in [\"id\", \"comment_text\", \"toxic\"]]], sep=',')\n",
-    "multi_train_df[\"target_text\"] = multi_train_df[\"target_text\"].apply(lambda x: \",\".join(word for word in x.split(\",\") if word)).apply(lambda x: x if x else \"clean\")\n",
-    "multi_train_df[\"input_text\"] = multi_train_df[\"comment_text\"].str.replace('\\n', ' ')\n",
+    "multi_train_df[\"target_text\"] = multi_train_df[\"toxic\"].str.cat(\n",
+    "    multi_train_df[\n",
+    "        [\n",
+    "            col\n",
+    "            for col in multi_train_df.columns\n",
+    "            if col not in [\"id\", \"comment_text\", \"toxic\"]\n",
+    "        ]\n",
+    "    ],\n",
+    "    sep=\",\",\n",
+    ")\n",
+    "multi_train_df[\"target_text\"] = (\n",
+    "    multi_train_df[\"target_text\"]\n",
+    "    .apply(lambda x: \",\".join(word for word in x.split(\",\") if word))\n",
+    "    .apply(lambda x: x if x else \"clean\")\n",
+    ")\n",
+    "multi_train_df[\"input_text\"] = multi_train_df[\"comment_text\"].str.replace(\"\\n\", \" \")\n",
     "multi_train_df[\"prefix\"] = \"multilabel classification\"\n",
     "multi_train_df = multi_train_df[[\"prefix\", \"input_text\", \"target_text\"]]\n",
     "\n",
@@ -206,15 +223,25 @@
     }
    ],
    "source": [
-    "prefix = 'data/regression/'\n",
+    "prefix = \"data/regression/\"\n",
     "\n",
-    "sts_train_df = pd.read_csv(prefix + 'train.tsv', sep='\\t', error_bad_lines=False).dropna()\n",
-    "sts_eval_df = pd.read_csv(prefix + 'dev.tsv', sep='\\t', error_bad_lines=False).dropna()\n",
+    "sts_train_df = pd.read_csv(\n",
+    "    prefix + \"train.tsv\", sep=\"\\t\", error_bad_lines=False\n",
+    ").dropna()\n",
+    "sts_eval_df = pd.read_csv(prefix + \"dev.tsv\", sep=\"\\t\", error_bad_lines=False).dropna()\n",
     "\n",
-    "sts_train_df[\"sentence1\"] = sts_train_df[\"sentence1\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
-    "sts_train_df[\"sentence2\"] = sts_train_df[\"sentence2\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
-    "sts_eval_df[\"sentence1\"] = sts_eval_df[\"sentence1\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
-    "sts_eval_df[\"sentence2\"] = sts_eval_df[\"sentence2\"].str.replace('\\n', ' ').str.replace('\\t', ' ')"
+    "sts_train_df[\"sentence1\"] = (\n",
+    "    sts_train_df[\"sentence1\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")\n",
+    "sts_train_df[\"sentence2\"] = (\n",
+    "    sts_train_df[\"sentence2\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")\n",
+    "sts_eval_df[\"sentence1\"] = (\n",
+    "    sts_eval_df[\"sentence1\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")\n",
+    "sts_eval_df[\"sentence2\"] = (\n",
+    "    sts_eval_df[\"sentence2\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")"
    ]
   },
   {
@@ -223,7 +250,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sts_train_df.drop(2001, inplace=True) # This line badly formatted. Getting rid."
+    "sts_train_df.drop(2001, inplace=True)  # This line badly formatted. Getting rid."
    ]
   },
   {
@@ -232,11 +259,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sts_train_df[\"input_text\"] = sts_train_df.apply(lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1)\n",
-    "sts_eval_df[\"input_text\"] = sts_eval_df.apply(lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1)\n",
+    "sts_train_df[\"input_text\"] = sts_train_df.apply(\n",
+    "    lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1\n",
+    ")\n",
+    "sts_eval_df[\"input_text\"] = sts_eval_df.apply(\n",
+    "    lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1\n",
+    ")\n",
     "\n",
-    "sts_train_df[\"target_text\"] = sts_train_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
-    "sts_eval_df[\"target_text\"] = sts_eval_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
+    "sts_train_df[\"target_text\"] = (\n",
+    "    sts_train_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
+    ")\n",
+    "sts_eval_df[\"target_text\"] = (\n",
+    "    sts_eval_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
+    ")\n",
     "\n",
     "sts_train_df[\"prefix\"] = \"similarity\"\n",
     "sts_eval_df[\"prefix\"] = \"similarity\"\n",

diff --git a/examples/t5/mt5/data_prep.ipynb b/examples/t5/mt5/data_prep.ipynb
@@ -37,30 +37,34 @@
     }
    ],
    "source": [
-    "prefix = 'data/binary_classification/'\n",
+    "prefix = \"data/binary_classification/\"\n",
     "\n",
-    "binary_train_df = pd.read_csv(prefix + 'train.csv', header=None)\n",
+    "binary_train_df = pd.read_csv(prefix + \"train.csv\", header=None)\n",
     "binary_train_df.head()\n",
     "\n",
-    "binary_eval_df = pd.read_csv(prefix + 'test.csv', header=None)\n",
+    "binary_eval_df = pd.read_csv(prefix + \"test.csv\", header=None)\n",
     "binary_eval_df.head()\n",
     "\n",
     "binary_train_df[0] = (binary_train_df[0] == 2).astype(int)\n",
     "binary_eval_df[0] = (binary_eval_df[0] == 2).astype(int)\n",
     "\n",
-    "binary_train_df = pd.DataFrame({\n",
-    "    'prefix': [\"binary classification\" for i in range(len(binary_train_df))],\n",
-    "    'input_text': binary_train_df[1].str.replace('\\n', ' '),\n",
-    "    'target_text': binary_train_df[0].astype(str),\n",
-    "})\n",
+    "binary_train_df = pd.DataFrame(\n",
+    "    {\n",
+    "        \"prefix\": [\"binary classification\" for i in range(len(binary_train_df))],\n",
+    "        \"input_text\": binary_train_df[1].str.replace(\"\\n\", \" \"),\n",
+    "        \"target_text\": binary_train_df[0].astype(str),\n",
+    "    }\n",
+    ")\n",
     "\n",
     "print(binary_train_df.head())\n",
     "\n",
-    "binary_eval_df = pd.DataFrame({\n",
-    "    'prefix': [\"binary classification\" for i in range(len(binary_eval_df))],\n",
-    "    'input_text': binary_eval_df[1].str.replace('\\n', ' '),\n",
-    "    'target_text': binary_eval_df[0].astype(str),\n",
-    "})\n",
+    "binary_eval_df = pd.DataFrame(\n",
+    "    {\n",
+    "        \"prefix\": [\"binary classification\" for i in range(len(binary_eval_df))],\n",
+    "        \"input_text\": binary_eval_df[1].str.replace(\"\\n\", \" \"),\n",
+    "        \"target_text\": binary_eval_df[0].astype(str),\n",
+    "    }\n",
+    ")\n",
     "\n",
     "\n",
     "print(binary_eval_df.head())"
@@ -156,16 +160,29 @@
    "source": [
     "prefix = \"data/multilabel_classification/\"\n",
     "\n",
-    "multi_train_df = pd.read_csv(prefix + 'train.csv')\n",
-    "multi_train_df[\"comment_text\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
+    "multi_train_df = pd.read_csv(prefix + \"train.csv\")\n",
+    "multi_train_df[\"comment_text\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
     "\n",
     "for col in multi_train_df.columns:\n",
     "    if col not in [\"id\", \"comment_text\"]:\n",
     "        multi_train_df[col] = multi_train_df[col].apply(lambda x: col if x else \"\")\n",
     "\n",
-    "multi_train_df[\"target_text\"] = multi_train_df['toxic'].str.cat(multi_train_df[[col for col in multi_train_df.columns if col not in [\"id\", \"comment_text\", \"toxic\"]]], sep=',')\n",
-    "multi_train_df[\"target_text\"] = multi_train_df[\"target_text\"].apply(lambda x: \",\".join(word for word in x.split(\",\") if word)).apply(lambda x: x if x else \"clean\")\n",
-    "multi_train_df[\"input_text\"] = multi_train_df[\"comment_text\"].str.replace('\\n', ' ')\n",
+    "multi_train_df[\"target_text\"] = multi_train_df[\"toxic\"].str.cat(\n",
+    "    multi_train_df[\n",
+    "        [\n",
+    "            col\n",
+    "            for col in multi_train_df.columns\n",
+    "            if col not in [\"id\", \"comment_text\", \"toxic\"]\n",
+    "        ]\n",
+    "    ],\n",
+    "    sep=\",\",\n",
+    ")\n",
+    "multi_train_df[\"target_text\"] = (\n",
+    "    multi_train_df[\"target_text\"]\n",
+    "    .apply(lambda x: \",\".join(word for word in x.split(\",\") if word))\n",
+    "    .apply(lambda x: x if x else \"clean\")\n",
+    ")\n",
+    "multi_train_df[\"input_text\"] = multi_train_df[\"comment_text\"].str.replace(\"\\n\", \" \")\n",
     "multi_train_df[\"prefix\"] = \"multilabel classification\"\n",
     "multi_train_df = multi_train_df[[\"prefix\", \"input_text\", \"target_text\"]]\n",
     "\n",
@@ -191,15 +208,25 @@
     }
    ],
    "source": [
-    "prefix = 'data/regression/'\n",
+    "prefix = \"data/regression/\"\n",
     "\n",
-    "sts_train_df = pd.read_csv(prefix + 'train.tsv', sep='\\t', error_bad_lines=False).dropna()\n",
-    "sts_eval_df = pd.read_csv(prefix + 'dev.tsv', sep='\\t', error_bad_lines=False).dropna()\n",
+    "sts_train_df = pd.read_csv(\n",
+    "    prefix + \"train.tsv\", sep=\"\\t\", error_bad_lines=False\n",
+    ").dropna()\n",
+    "sts_eval_df = pd.read_csv(prefix + \"dev.tsv\", sep=\"\\t\", error_bad_lines=False).dropna()\n",
     "\n",
-    "sts_train_df[\"sentence1\"] = sts_train_df[\"sentence1\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
-    "sts_train_df[\"sentence2\"] = sts_train_df[\"sentence2\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
-    "sts_eval_df[\"sentence1\"] = sts_eval_df[\"sentence1\"].str.replace('\\n', ' ').str.replace('\\t', ' ')\n",
-    "sts_eval_df[\"sentence2\"] = sts_eval_df[\"sentence2\"].str.replace('\\n', ' ').str.replace('\\t', ' ')"
+    "sts_train_df[\"sentence1\"] = (\n",
+    "    sts_train_df[\"sentence1\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")\n",
+    "sts_train_df[\"sentence2\"] = (\n",
+    "    sts_train_df[\"sentence2\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")\n",
+    "sts_eval_df[\"sentence1\"] = (\n",
+    "    sts_eval_df[\"sentence1\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")\n",
+    "sts_eval_df[\"sentence2\"] = (\n",
+    "    sts_eval_df[\"sentence2\"].str.replace(\"\\n\", \" \").str.replace(\"\\t\", \" \")\n",
+    ")"
    ]
   },
   {
@@ -208,7 +235,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sts_train_df.drop(2001, inplace=True) # This line badly formatted. Getting rid."
+    "sts_train_df.drop(2001, inplace=True)  # This line badly formatted. Getting rid."
    ]
   },
   {
@@ -217,11 +244,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sts_train_df[\"input_text\"] = sts_train_df.apply(lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1)\n",
-    "sts_eval_df[\"input_text\"] = sts_eval_df.apply(lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1)\n",
+    "sts_train_df[\"input_text\"] = sts_train_df.apply(\n",
+    "    lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1\n",
+    ")\n",
+    "sts_eval_df[\"input_text\"] = sts_eval_df.apply(\n",
+    "    lambda x: \"sentence1: \" + x[\"sentence1\"] + \" sentence2: \" + x[\"sentence2\"], axis=1\n",
+    ")\n",
     "\n",
-    "sts_train_df[\"target_text\"] = sts_train_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
-    "sts_eval_df[\"target_text\"] = sts_eval_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
+    "sts_train_df[\"target_text\"] = (\n",
+    "    sts_train_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
+    ")\n",
+    "sts_eval_df[\"target_text\"] = (\n",
+    "    sts_eval_df[\"score\"].apply(lambda x: round(x * 5) / 5).astype(str)\n",
+    ")\n",
     "\n",
     "sts_train_df[\"prefix\"] = \"similarity\"\n",
     "sts_eval_df[\"prefix\"] = \"similarity\"\n",

diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name="simpletransformers",
-    version="0.64.3",
+    version="0.64.5",
     author="Thilina Rajapakse",
     author_email="[email protected]",
     description="An easy-to-use wrapper library for the Transformers library.",
@@ -32,6 +32,7 @@
         "scikit-learn",
         "seqeval",
         "tensorboard",
+        "tensorboardx",
         "pandas",
         "tokenizers",
         "wandb>=0.10.32",

diff --git a/simpletransformers/classification/classification_model.py b/simpletransformers/classification/classification_model.py
@@ -182,7 +182,6 @@ def __init__(
         onnx_execution_provider=None,
         **kwargs,
     ):
-
         """
         Initializes a ClassificationModel model.
 
@@ -1641,10 +1640,14 @@ def evaluate(
 
             if not self.args.sliding_window:
                 # ROC`
-                wandb.log({"roc": wandb.plot.roc_curve(truth, model_outputs, labels_list)})
+                wandb.log(
+                    {"roc": wandb.plot.roc_curve(truth, model_outputs, labels_list)}
+                )
 
                 # Precision Recall
-                wandb.log({"pr": wandb.plot.pr_curve(truth, model_outputs, labels_list)})
+                wandb.log(
+                    {"pr": wandb.plot.pr_curve(truth, model_outputs, labels_list)}
+                )
 
         return results, model_outputs, wrong
 

diff --git a/simpletransformers/classification/classification_utils.py b/simpletransformers/classification/classification_utils.py
@@ -803,7 +803,6 @@ def __init__(
         data_type_extension=None,
         multi_label=False,
     ):
-
         self.text_label = text_label if text_label else "text"
         self.labels_label = labels_label if labels_label else "labels"
         self.images_label = images_label if images_label else "images"

diff --git a/simpletransformers/classification/multi_label_classification_model.py b/simpletransformers/classification/multi_label_classification_model.py
@@ -89,7 +89,6 @@ def __init__(
         cuda_device=-1,
         **kwargs,
     ):
-
         """
         Initializes a MultiLabelClassification model.
 

diff --git a/simpletransformers/classification/multi_modal_classification_model.py b/simpletransformers/classification/multi_modal_classification_model.py
@@ -86,7 +86,6 @@ def __init__(
         cuda_device=-1,
         **kwargs,
     ):
-
         """
         Initializes a MultiModalClassificationModel model.
 

diff --git a/simpletransformers/classification/transformer_models/albert_model.py b/simpletransformers/classification/transformer_models/albert_model.py
@@ -56,7 +56,6 @@ def forward(
         inputs_embeds=None,
         labels=None,
     ):
-
         outputs = self.albert(
             input_ids=input_ids,
             attention_mask=attention_mask,

diff --git a/simpletransformers/classification/transformer_models/bert_model.py b/simpletransformers/classification/transformer_models/bert_model.py
@@ -53,7 +53,6 @@ def forward(
         inputs_embeds=None,
         labels=None,
     ):
-
         outputs = self.bert(
             input_ids,
             attention_mask=attention_mask,

diff --git a/simpletransformers/classification/transformer_models/electra_model.py b/simpletransformers/classification/transformer_models/electra_model.py
@@ -55,7 +55,6 @@ def forward(
         inputs_embeds=None,
         labels=None,
     ):
-
         discriminator_hidden_states = self.electra(
             input_ids,
             attention_mask,

diff --git a/simpletransformers/classification/transformer_models/layoutlm_model.py b/simpletransformers/classification/transformer_models/layoutlm_model.py
@@ -27,7 +27,6 @@ def forward(
         inputs_embeds=None,
         labels=None,
     ):
-
         outputs = self.bert(
             input_ids=input_ids,
             bbox=bbox,
-Original file line number
+Diff line change
@@ Expand Up / @@ -89,7 +89,6 @@ def __init__( @@
             cuda_device=-1,
             **kwargs,
         ):
             """
             Initializes a MultiLabelClassification model.
@@ Expand Down @@