Experiment #2

Experiments.py

@@ -8,59 +8,53 @@ from data_code_run import DataCodeRun
 load_dotenv()  # take environment variables from .env.
 os.environ['GEMINI_API_KEY'] = os.getenv("GOOGLE_API_KEY")
 
-file_path = './test_data.csv'
-df = pd.read_csv(file_path)
 
-string_data= df.to_string(index=False)
+def LLM_summary():
+    file_path = './test_data.csv'
+    df = pd.read_csv(file_path)
+
+    string_data= df.to_string(index=False)
+
+    # Get column names
+    column_names = ", ".join(df.columns.tolist())
+        
+    # Get data types
+    data_types = ", ".join([f"{col}: {dtype}" for col, dtype in df.dtypes.items()])
+        
+    # Get number of rows and columns
+    num_rows, num_cols = df.shape
+        
+    # Construct the dataset information string
+    info_string = f"Dataset Information:\n"
+    info_string += f"Columns: {column_names}\n"
+    info_string += f"Data Types: {data_types}\n"
+    info_string += f"Number of Rows: {num_rows}\n"
+    info_string += f"Number of Columns: {num_cols}\n"
 
-# Get column names
-column_names = ", ".join(df.columns.tolist())
     
-# Get data types
-data_types = ", ".join([f"{col}: {dtype}" for col, dtype in df.dtypes.items()])
     
-# Get number of rows and columns
-num_rows, num_cols = df.shape
+    message = f'''
+    You are a data analyser agent working with a given dataset.
+    Below is the info about the dataset -
+    ========
+    {info_string}
+    ========
+
+    Your task -
+    Write a summary report of the dataset. You have to explain what the dataset is about and what kind of information could be gained from the dataset.
     
-# Construct the dataset information string
-info_string = f"Dataset Information:\n"
-info_string += f"Columns: {column_names}\n"
-info_string += f"Data Types: {data_types}\n"
-info_string += f"Number of Rows: {num_rows}\n"
-info_string += f"Number of Columns: {num_cols}\n"
 
-# print(string_data)
-request = "total number of null values in all columns"
-message = f'''
-You are a data analyser agent working with a given dataset.
-Below is the info about the dataset -
+    Do not infer any data based on previous training, strictly use only source text given below as input.
 
-========
-{info_string}
-========
+    '''
+    output = completion(
+        model="gemini/gemini-pro", 
+        messages=[
+                {"role": "user", "content": message}
+            ]
+    )
 
-Your task -
-write a proper prompt to tell another agent to generate code to fulfill the below request by the user.
-You have to give all the details about the columns involved and only the required info about the dataset needed to fulfil the request.
-failues are given as 0 and 1 in target column. Also tell about the file location that is 'test_data.csv'.
+    print(output.choices[0].message.content)
 
-Request : 
-=======
-{request}
-=======
-Do not infer any data based on previous training, strictly use only source text given below as input.
-
-'''
-output = completion(
-    model="gemini/gemini-pro", 
-    messages=[
-            {"role": "user", "content": message}
-        ]
-)
-
-print(output.choices[0].message.content)
-
-message = output.choices[0].message.content
-runner = DataCodeRun()
-
-runner.run_code(message)
+    
+LLM_summary()

code.py

@@ -1,10 +0,0 @@
-import pandas as pd
-
-# Load the dataset
-df = pd.read_csv('test_data.csv')
-
-# Count the number of null values in each column
-null_counts = df.isnull().sum()
-
-# Print the total number of null values
-print(null_counts.sum())

data.csv

@@ -1,101 +0,0 @@
-X,Y
-3.745401188,16.4102977
-9.507143064,32.92341449
-7.319939418,27.14333981
-5.986584842,18.9846167
-1.560186404,9.241215438
-1.559945203,10.39406075
-0.580836122,9.698296455
-8.661761458,29.94874394
-6.011150117,21.41646315
-7.080725778,25.23866325
-0.205844943,7.448339064
-9.699098522,34.75479778
-8.324426408,28.91375882
-2.123391107,12.39670819
-1.818249672,10.64890411
-1.834045099,12.43942528
-3.04242243,12.7231611
-5.247564316,20.08736866
-4.319450186,17.17413425
-2.912291402,10.80984431
-6.118528947,23.9478274
-1.394938607,9.706926364
-2.921446485,13.77456637
-3.663618433,15.52168103
-4.560699842,15.85135804
-7.851759614,27.7139882
-1.996737822,10.30478443
-5.142344384,18.82247861
-4.626727484443299,22.44986564
-0.464504127,7.201614095
-6.075448519,26.99871736
-1.705241237,10.46487934
-0.65051593,7.466648571
-9.488855373,33.31767429
-9.656320331,30.13141856
-8.083973481,19.07749914296875
-3.046137692,14.2588735
-0.97672114,12.85664765
-6.842330265,25.14226887
-4.401524937,18.8076695
-1.220382348,8.591723506
-4.951769101,17.51795123
-0.343885211,8.317301262
-9.093204021,19.07749914296875
-2.587799816,14.34546334
-6.625222844,23.05689362
-3.117110761,17.1569209
-5.200680212,17.79833851
-5.467102793,22.57502257
-1.848544555,14.92654492
-9.695846278,32.10646618
-4.626727484443299,27.12138924
-9.394989416,33.38427098
-8.948273504,30.8378692
-5.978999788,19.8356725
-9.21874235,32.793353
-0.884925021,5.530167634
-1.959828624,11.82667073
-0.452272889,4.517970199
-3.253303308,17.85977873
-3.886772897,15.09381211
-2.713490318,12.49634792
-8.287375092,31.48915971
-3.567533267,13.24087117
-2.809345097,13.88295516
-5.426960832,23.895168
-1.40924225,19.07749914296875
-8.021969808,29.43517714
-0.745506437,7.756284899
-9.868869366,36.17025384
-7.722447693,25.69344166
-1.987156815,8.32055722
-0.055221171,6.209546645
-8.154614285,30.0578122
-7.068573438,26.70670602
-7.29007168,27.56311146
-4.626727484443299,26.77806096
-0.740446517,7.685846946
-3.584657285,16.3401168
-1.158690595,7.04736895
-8.631034259,34.6246518
-6.232981268,24.64660965
-3.308980249,12.54433375
-0.635583503,8.219857726
-3.109823217,12.38010631
-3.25183322,16.32966887
-7.296061783,29.20537651
-6.375574714,22.4853595
-8.872127426,33.54313454
-4.722149252,19.99200961
-1.195942459,10.2319477
-7.132447872,30.19092958
-7.607850486,27.33277523
-5.612771976,20.3308436
-7.7096718,26.34998654
-4.937955964,18.18224732
-5.227328294,20.52778146
-4.275410184,18.5085345
-0.254191267,6.315955401
-1.07891427,19.07749914296875