Update app.py

app.py

@@ -69,7 +69,8 @@ agent = ReactCodeAgent(
 
 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 5 interesting questions that could be asked on this data, for instance about specific correlations with target variable.
+If a user asks a very specific question, then just answer that question by performing data exploration. If not, then list 5 interesting questions that could be asked on this data by examining the metadata of the columns, for instance about specific correlations with target variable.
+For example, outlier analysis and trend analysis are considered interesting questions.
 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.
 Generate a summary of each of the plot generated.