Dacho688 commited on
Commit
69b18c8
·
1 Parent(s): 42c2cb4
README.md CHANGED
@@ -5,6 +5,7 @@ colorFrom: yellow
5
  colorTo: red
6
  sdk: gradio
7
  sdk_version: 4.38.1
 
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
 
5
  colorTo: red
6
  sdk: gradio
7
  sdk_version: 4.38.1
8
+ python_version: 3.9
9
  app_file: app.py
10
  pinned: false
11
  license: apache-2.0
__pycache__/streaming.cpython-311.pyc CHANGED
Binary files a/__pycache__/streaming.cpython-311.pyc and b/__pycache__/streaming.cpython-311.pyc differ
 
app.py CHANGED
@@ -5,7 +5,7 @@ from transformers import ReactCodeAgent, HfEngine, Tool
5
  import pandas as pd
6
 
7
  from gradio import Chatbot
8
- from streaming import stream_to_gradio
9
  from huggingface_hub import login
10
  from gradio.data_classes import FileData
11
 
@@ -20,22 +20,18 @@ agent = ReactCodeAgent(
20
  max_iterations=10,
21
  )
22
 
23
- base_prompt = """You are an expert data analyst.
24
  You are given a data file and the data structure below.
25
  The data file is passed to you as the variable data_file, it is a pandas dataframe, you can use it directly.
26
  DO NOT try to load data_file, it is already a dataframe pre-loaded in your python interpreter!
27
-
 
28
  When importing packages use this format: from package import module
29
  For example: from matplotlib import pyplot as plt
30
  Not: import matplotlib.pyplot as plt
31
 
32
- As you work, check for NoneType values and convert to NAN.
33
-
34
  Use the data file to answer the question or solve a problem given below.
35
 
36
- In your final answer: summarize your findings
37
- 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".
38
-
39
  Structure of the data:
40
  {structure_notes}
41
 
 
5
  import pandas as pd
6
 
7
  from gradio import Chatbot
8
+ from test_streaming import stream_to_gradio
9
  from huggingface_hub import login
10
  from gradio.data_classes import FileData
11
 
 
20
  max_iterations=10,
21
  )
22
 
23
+ base_prompt = """You are an expert full stack data analyst.
24
  You are given a data file and the data structure below.
25
  The data file is passed to you as the variable data_file, it is a pandas dataframe, you can use it directly.
26
  DO NOT try to load data_file, it is already a dataframe pre-loaded in your python interpreter!
27
+ When plotting using matplotlib/seaborn save the figures to the (already existing) folder'./figures/': take care to clear each figure with plt.clf() before doing another plot.
28
+ When filtering pandas dataframe use the iloc.
29
  When importing packages use this format: from package import module
30
  For example: from matplotlib import pyplot as plt
31
  Not: import matplotlib.pyplot as plt
32
 
 
 
33
  Use the data file to answer the question or solve a problem given below.
34
 
 
 
 
35
  Structure of the data:
36
  {structure_notes}
37
 
requirements.txt CHANGED
@@ -4,6 +4,7 @@ seaborn
4
  scikit-learn
5
  scipy
6
  transformers
7
- pandas==2.2.2
8
  huggingface_hub
9
- transformers
 
 
4
  scikit-learn
5
  scipy
6
  transformers
7
+ pandas
8
  huggingface_hub
9
+ numpy
10
+ pandas