try to read_csv2

.idea/workspace.xml

@@ -31,6 +31,34 @@
     <property name="last_opened_file_path" value="$PROJECT_DIR$" />
     <property name="settings.editor.selected.configurable" value="com.jetbrains.python.configuration.PyActiveSdkModuleConfigurable" />
   </component>
+  <component name="RunManager">
+    <configuration name="app" type="PythonConfigurationType" factoryName="Python" temporary="true" nameIsGenerated="true">
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="C:\Users\borod\AppData\Local\Programs\Python\Python37\python.exe" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="false" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <module name="" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/app.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+    <recent_temporary>
+      <list>
+        <item itemvalue="Python.app" />
+      </list>
+    </recent_temporary>
+  </component>
   <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
   <component name="TaskManager">
     <task active="true" id="Default" summary="Default task">

app.py

@@ -1,4 +1,40 @@
 import gradio as gr
+from re import sub
+from datasets import load_dataset
+import pandas as pd
+
+
+def clean_text(text):
+    """
+    Applies some pre-processing on the given text.
+
+    Steps :
+    - Lowering text
+    - Removing backslashes
+    - removes a. out of the answers
+    - replaces 'b.', 'c.', and 'd.' with comma ','
+    """
+    text = text.lower()
+    text = text.replace('\\', '')  # generic replace was advised by Danit
+    text = text.replace('a.', '')
+    text = text.replace('b.', ',')
+    text = text.replace('c.', ',')
+    text = text.replace('d.', ',')
+    text = sub("\d+", "<num>", text)
+
+    return ' '.join(text.split())
+
+
+dataset = load_dataset(
+    "csv",
+    data_files={
+        "train": "https://huggingface.co/borodache/science-classification/resolve/main/subjects-questions.csv"
+    },
+    use_auth_token=True,
+)
+
+
+# df = pd.read_csv("/subjects-questions.csv")
 
 
 def greet(name):

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+datasets
+pandas