Create test.py

test.py

@@ -0,0 +1,91 @@
+import pandas as pd
+import re
+
+# Example text extracted from the provided screenshot
+llm_response = """
+Table 1: Biomarker Results
+Biomarker | Method | Result
+--- | --- | ---
+Microsatellite Instability (MSI) | NGS | Stable
+Tumor Mutational Burden (TMB) | NGS | Low
+
+Table 2: Gene Mutations
+Gene | Method | Variant | Interpretation | Protein Alteration | Exon | DNA Alteration | Variant Frequency (%)
+--- | --- | --- | --- | --- | --- | --- | ---
+ARID1A | NGS | Mutated, Pathogenic | p.P227fs | | | 24 |
+CDKN2A | NGS | Mutated, Pathogenic | p.W15* | | | 26 |
+KRAS | NGS | Mutated, Pathogenic | p.G12D | | | 32 |
+TP53 | NGS | Mutated, Pathogenic | p.Y163C | | | 29 |
+
+Table 3: Other Findings
+Biomarker | Result
+--- | ---
+MLH1 | Positive
+PD-L1 | Negative
+MSH2 | Positive
+PMS2 | Positive
+MSH6 | Positive
+
+Table 4: Genes Tested Without Point Mutations or Indels
+Genes | Tested
+--- | ---
+BRCA2 | 
+EGFR | 
+IDH1 | 
+KIT | 
+MET | 
+NRAS | 
+NTRK1 | 
+NTRK2 | 
+Neu | 
+NTRK3 | 
+ERBB2 | 
+ATM | 
+BRAF | 
+PDGFRA | 
+PIK3CA | 
+RET | 
+SMARCB1 |
+"""
+
+# Function to parse tables from the response
+def parse_tables(response_text):
+    tables = {}
+    current_table = []
+    current_table_name = None
+
+    for line in response_text.strip().split('\n'):
+        if line.startswith("Table"):
+            if current_table_name:
+                tables[current_table_name] = current_table
+            current_table_name = re.sub(r'Table \d+: ', '', line)
+            current_table = []
+        else:
+            current_table.append(line.strip())
+
+    if current_table_name:
+        tables[current_table_name] = current_table
+
+    return tables
+
+# Function to convert parsed tables into DataFrames
+def tables_to_dataframes(parsed_tables):
+    dataframes = {}
+    for table_name, lines in parsed_tables.items():
+        if len(lines) > 2:
+            headers = lines[1].split(" | ")
+            data = [row.split(" | ") for row in lines[2:]]
+            df = pd.DataFrame(data, columns=headers)
+            dataframes[table_name] = df
+    return dataframes
+
+# Parse the tables
+parsed_tables = parse_tables(llm_response)
+
+# Convert tables to DataFrames
+dataframes = tables_to_dataframes(parsed_tables)
+
+# Display dataframes
+for table_name, df in dataframes.items():
+    print(f"\n{table_name}:\n")
+    print(df)