Update app.py

app.py

@@ -12,7 +12,7 @@ from gradio.data_classes import FileData
 # Log in to Hugging Face
 login(os.getenv("HUGGINGFACEHUB_API_TOKEN"))
 
-# Initialize the LLM engine
+# Initialize the LLM engine with an Arabic model
 llm_engine = HfEngine("Rohan-Kurdekar/Arabic_Bert_Model")
 
 # Initialize the agent
@@ -26,12 +26,12 @@ agent = ReactCodeAgent(
 # Define the base prompt
 base_prompt = """You are an expert data analyst.
 According to the features you have and the data structure given below, determine which feature should be the target.
-Then list 3 interesting questions that could be asked on this data, for instance about specific correlations with target variable.
+Then list 3 interesting questions that could be asked on this data, for instance about specific correlations with the target variable.
 Then answer these questions one by one, by finding the relevant numbers.
 Meanwhile, plot some figures using matplotlib/seaborn and save them to the (already existing) folder './figures/': take care to clear each figure with plt.clf() before doing another plot.
 
-In your final answer: summarize these correlations and trends
-After each number derive real worlds insights, for instance: "Correlation between is_december and boredness is 1.3453, which suggest people are more bored in winter".
+In your final answer: summarize these correlations and trends.
+After each number derive real world insights, for instance: "Correlation between is_december and boredness is 1.3453, which suggest people are more bored in winter".
 Your final answer should be a long string with at least 3 numbered and detailed parts.
 
 Structure of the data:
@@ -41,22 +41,6 @@ The data file is passed to you as the variable data_file, it is a pandas datafra
 DO NOT try to load data_file, it is already a dataframe pre-loaded in your python interpreter!
 """
 
-# Example notes
-example_notes = """This data is about the Titanic wreck in 1912.
-The target figure is the survival of passengers, noted by 'Survived'
-pclass: A proxy for socio-economic status (SES)
-1st = Upper
-2nd = Middle
-3rd = Lower
-age: Age is fractional if less than 1. If the age is estimated, is it in the form of xx.5
-sibsp: The dataset defines family relations in this way...
-Sibling = brother, sister, stepbrother, stepsister
-Spouse = husband, wife (mistresses and fiancés were ignored)
-parch: The dataset defines family relations in this way...
-Parent = mother, father
-Child = daughter, son, stepdaughter, stepson
-Some children travelled only with a nanny, therefore parch=0 for them."""
-
 def get_images_in_directory(directory):
     image_extensions = {'.png', '.jpg', '.jpeg', '.gif', '.bmp', '.tiff'}
     image_files = []
@@ -74,7 +58,8 @@ def interact_with_agent(file_input, additional_notes):
             shutil.rmtree(figures_dir)
         os.makedirs(figures_dir)
 
-        data_file = pd.read_csv(file_input)
+        # Read the CSV file with the appropriate encoding for Arabic text
+        data_file = pd.read_csv(file_input.name, encoding='utf-8')
         data_structure_notes = f"""- Description (output of .describe()):
         {data_file.describe()}
         - Columns with dtypes: