Mollel commited on
Commit
a323ffa
·
verified ·
1 Parent(s): ae12324

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +29 -2
app.py CHANGED
@@ -21,6 +21,31 @@ def extract_table_from_markdown(markdown_text, table_start):
21
  table_content.append(line)
22
  return '\n'.join(table_content)
23
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  def markdown_table_to_df(table_content):
25
  """Convert markdown table to pandas DataFrame."""
26
  # Split the table content into lines
@@ -33,8 +58,10 @@ def markdown_table_to_df(table_content):
33
  data = []
34
  for line in lines[2:]: # Skip the header separator line
35
  row = [cell.strip() for cell in line.split('|') if cell.strip()]
36
- if row and len(row) == len(headers): # Ensure row has the correct number of columns
37
- data.append(row)
 
 
38
 
39
  # Create DataFrame
40
  df = pd.DataFrame(data, columns=headers)
 
21
  table_content.append(line)
22
  return '\n'.join(table_content)
23
 
24
+ # def markdown_table_to_df(table_content):
25
+ # """Convert markdown table to pandas DataFrame."""
26
+ # # Split the table content into lines
27
+ # lines = table_content.split('\n')
28
+
29
+ # # Extract headers
30
+ # headers = [h.strip() for h in lines[0].split('|') if h.strip()]
31
+
32
+ # # Extract data
33
+ # data = []
34
+ # for line in lines[2:]: # Skip the header separator line
35
+ # row = [cell.strip() for cell in line.split('|') if cell.strip()]
36
+ # if row and len(row) == len(headers): # Ensure row has the correct number of columns
37
+ # data.append(row)
38
+
39
+ # # Create DataFrame
40
+ # df = pd.DataFrame(data, columns=headers)
41
+
42
+ # # Convert numeric columns to float
43
+ # for col in df.columns:
44
+ # if col not in ["Model Name", "Publisher", "Open?", "Basemodel", "Matryoshka"]:
45
+ # df[col] = pd.to_numeric(df[col], errors='coerce')
46
+
47
+ # return df
48
+
49
  def markdown_table_to_df(table_content):
50
  """Convert markdown table to pandas DataFrame."""
51
  # Split the table content into lines
 
58
  data = []
59
  for line in lines[2:]: # Skip the header separator line
60
  row = [cell.strip() for cell in line.split('|') if cell.strip()]
61
+ if row: # Include any non-empty row
62
+ # Pad the row with empty strings if it's shorter than the headers
63
+ padded_row = row + [''] * (len(headers) - len(row))
64
+ data.append(padded_row[:len(headers)]) # Trim if longer than headers
65
 
66
  # Create DataFrame
67
  df = pd.DataFrame(data, columns=headers)