A quick script to format tables that were in the `verbatim` environment as proper tables using Pandas.

latex_table_maker.py

#!python3
"""
A script to read a document containing tables that I left as "verbatim" and 
format them properly in LaTeX.

We go from this:

\begin{verbatim}
          sparsity   num_active     accuracy  test_accuracy  train_accuracy
count  4000.000000  4000.000000  4000.000000    4000.000000            4000
mean      0.984240   124.657750     0.957216       0.829739               1
std       0.000943     7.460431     0.020602       0.079698               0
min       0.981290    94.000000     0.864583       0.500000               1
25%       0.983565   119.000000     0.947917       0.772727               1
50%       0.984197   125.000000     0.958333       0.833333               1
75%       0.984956   130.000000     0.968750       0.875000               1
max       0.988116   148.000000     1.000000       1.000000               1
\end{verbatim}

to this:

\begin{tabular}{lrrrrr}
\toprule
{} & sparsity & num\_active & accuracy & test\_accuracy & train\_accuracy \\
\midrule
mean &   0.9842 &   124.6577 &   0.9572 &        0.8297 &         1.0000 \\
std  &   0.0009 &     7.4604 &   0.0206 &        0.0797 &         0.0000 \\
min  &   0.9813 &    94.0000 &   0.8646 &        0.5000 &         1.0000 \\
25\%  &   0.9836 &   119.0000 &   0.9479 &        0.7727 &         1.0000 \\
50\%  &   0.9842 &   125.0000 &   0.9583 &        0.8333 &         1.0000 \\
75\%  &   0.9850 &   130.0000 &   0.9688 &        0.8750 &         1.0000 \\
max  &   0.9881 &   148.0000 &   1.0000 &        1.0000 &         1.0000 \\
\bottomrule
\end{tabular}
"""
import pandas as pd 
import sys

def read_table(text, separator=None, linebreak='\n', header=True, index=True):
    def parse_row(line):
        return [x.strip() for x in line.split(separator)]
    rows = text.split(linebreak)
    # name the columns according to the first row, if desired
    if header:
        cols = parse_row(rows.pop(0))
    else:
        cols = None

    # parse each row
    data = [parse_row(x) for x in rows]
    
    # if we want to keep the index separate, we can do so
    if index:
        indices = [x.pop(0) for x in data]
    else:
        indices = None
    # convert to a pandas dataframe
    return pd.DataFrame(data, columns=cols, index=indices)

def my_df_format(df):
    """Quick and dirty formatting of a dataframe. Adapt as necessary."""
    # sparsity num_active accuracy test_accuracy, train_accuracy
    df = df.copy()
    df = df.drop(['count'])
    dtypes = {
        'sparsity': float,
        'num_active': float,
        'accuracy': float,
        'test_accuracy': float,
        'train_accuracy': float,
    }
    for k, v in dtypes.items():
        df[k] = df[k].astype(v)

    formats = {
        'sparsity': '{:.4f}'.format,
        'num_active': '{:.4f}'.format,
        'accuracy': '{:.4f}'.format,
        'test_accuracy': '{:.4f}'.format,
        'train_accuracy': '{:.4f}'.format,
    }
    # print(df.to_latex(formatters=formats))
    return df.to_latex(formatters=formats)

def format_document(filename):
    """Process the document; a bit of a kludge."""
    with open(filename, 'r') as f:
        lines = f.readlines()
    ret = []

    in_table = False
    for line in lines:
        # print(line)
        if r'\begin{verbatim}' in line:
            if in_table:
                raise Exception('Looks like something went wrong') # exceptional exception
            else:
                in_table = True
            tmp = []
        elif in_table:
            if r'\end{verbatim}' in line:
                txt = ''.join(tmp).strip()
                # print(txt)
                df = read_table(txt)
                ret.append(my_df_format(df))
                in_table = False
            else:
                tmp.append(line)
        else:
            ret.append(line)
    return ''.join(ret)


# Get the name of the file to operate on, and optionally an output
if __name__ == "__main__":
    txt = format_document(sys.argv[1])
    if len(sys.argv) > 2:
        open(sys.argv[2], 'w').write(txt)
    else:
        print(txt)