Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -16,12 +16,12 @@ llm_engine = HfEngine("meta-llama/Meta-Llama-3.1-70B-Instruct")
|
|
16 |
agent = ReactCodeAgent(
|
17 |
tools=[],
|
18 |
llm_engine=llm_engine,
|
19 |
-
additional_authorized_imports=["numpy", "pandas", "matplotlib.pyplot", "seaborn"],
|
20 |
max_iterations=10,
|
21 |
)
|
22 |
|
23 |
base_prompt = """You are an expert data analyst.
|
24 |
-
According to the features you have and the
|
25 |
Then list 3 interesting questions that could be asked on this data, for instance about specific correlations with target variable.
|
26 |
Then answer these questions one by one, by finding the relevant numbers.
|
27 |
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.
|
|
|
16 |
agent = ReactCodeAgent(
|
17 |
tools=[],
|
18 |
llm_engine=llm_engine,
|
19 |
+
additional_authorized_imports=["numpy", "pandas", "matplotlib.pyplot", "seaborn", "scipy.stats"],
|
20 |
max_iterations=10,
|
21 |
)
|
22 |
|
23 |
base_prompt = """You are an expert data analyst.
|
24 |
+
According to the features you have and the data structure given below, determine which feature should be the target.
|
25 |
Then list 3 interesting questions that could be asked on this data, for instance about specific correlations with target variable.
|
26 |
Then answer these questions one by one, by finding the relevant numbers.
|
27 |
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.
|