plotair 0.2.1__tar.gz → 0.3.0__tar.gz

{plotair-0.2.1 → plotair-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: plotair
-Version: 0.2.1
+Version: 0.3.0
 Summary: Generate CO₂, humidity and temperature plots from VisiblAir sensor CSV files.
 Project-URL: Repository, https://github.com/monsieurlinux/plotair
 Author-email: Monsieur Linux <info@mlinux.ca>
@@ -94,7 +94,20 @@ plotair [arguments] FILE [FILE ...]
 
 ### Command-Line Arguments
 
-None for now.
+| Argument              | Short Flag | Description                                          |
+| --------------------- | ---------- | ---------------------------------------------------- |
+| `--help`              | `-h`       | Show help message                                    |
+| `--all-dates`         | `-a`       | Plot all dates (otherwise only latest sequence)      |
+| `--boxplot`           | `-b`       | Generate boxplots along with text stats              |
+| `--merge`             | `-m`       | Merge field from file1 to file2, and output to file3 |
+| `--filter-multiplier` | `-M`       | Multiplier for IQR outlier filtering (default: 1.5)  |
+| `--filter-outliers`   | `-o`       | Filter out outliers from the plots                   |
+| `--reset-config`      | `-r`       | Reset configuration file to default                  |
+| `--start-date`        | `-s`       | Date at which to start the plot (YYYY-MM-DD)         |
+| `--stop-date`         | `-S`       | Date at which to stop the plot (YYYY-MM-DD)          |
+| `--title`             | `-t`       | Set the plot title                                   |
+| `--snapshots`         | `-T`       | Generate a snapshots table from all files            |
+| `--version`           | `-v`       | Show program's version number and exit               |
 
 ## Configuration
 

{plotair-0.2.1 → plotair-0.3.0}/README.md

@@ -78,7 +78,20 @@ plotair [arguments] FILE [FILE ...]
 
 ### Command-Line Arguments
 
-None for now.
+| Argument              | Short Flag | Description                                          |
+| --------------------- | ---------- | ---------------------------------------------------- |
+| `--help`              | `-h`       | Show help message                                    |
+| `--all-dates`         | `-a`       | Plot all dates (otherwise only latest sequence)      |
+| `--boxplot`           | `-b`       | Generate boxplots along with text stats              |
+| `--merge`             | `-m`       | Merge field from file1 to file2, and output to file3 |
+| `--filter-multiplier` | `-M`       | Multiplier for IQR outlier filtering (default: 1.5)  |
+| `--filter-outliers`   | `-o`       | Filter out outliers from the plots                   |
+| `--reset-config`      | `-r`       | Reset configuration file to default                  |
+| `--start-date`        | `-s`       | Date at which to start the plot (YYYY-MM-DD)         |
+| `--stop-date`         | `-S`       | Date at which to stop the plot (YYYY-MM-DD)          |
+| `--title`             | `-t`       | Set the plot title                                   |
+| `--snapshots`         | `-T`       | Generate a snapshots table from all files            |
+| `--version`           | `-v`       | Show program's version number and exit               |
 
 ## Configuration
 

plotair-0.3.0/plotair/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.0"

{plotair-0.2.1 → plotair-0.3.0}/plotair/config.toml

@@ -25,7 +25,7 @@ co2 = [0, 2000]
 humidity = [0, 80]
 temp = [0, 80]
 tvoc = [0, 500]
-co = [0, 50]
+co = [0, 6]
 form = [0, 50]
 "pm2.5" = [0, 70]
 "pm10" = [0, 70]

{plotair-0.2.1 → plotair-0.3.0}/plotair/main.py

@@ -57,10 +57,10 @@ def main():
                         help='generate boxplots along with text stats')
     parser.add_argument('-m', '--merge', metavar='FIELD',
                         help='merge field from file1 to file2, and output to file3')
+    parser.add_argument('-M', '--filter-multiplier', type=float, default=1.5, metavar='MULTIPLIER',
+                        help='multiplier for IQR outlier filtering (default: 1.5)')
     parser.add_argument('-o', '--filter-outliers', action='store_true',
                         help='filter out outliers from the plots')
-    parser.add_argument('--filter-multiplier', type=float, default=1.5, metavar='MULTIPLIER',
-                        help='multiplier for IQR outlier filtering (default: 1.5)')
     parser.add_argument('-r', '--reset-config', action='store_true',
                         help='reset configuration file to default')
     parser.add_argument('-s', '--start-date', metavar='DATE',
@@ -69,7 +69,9 @@ def main():
                         help='date at which to stop the plot (YYYY-MM-DD)')
     parser.add_argument('-t', '--title',
                         help='set the plot title')
-    parser.add_argument('-v', '--version', action='version', 
+    parser.add_argument('-T', '--snapshots', action='store_true',
+                        help='generate a snapshots table from all files')
+    parser.add_argument('-v', '--version', action='version',
                         version=f'%(prog)s {__version__}')
 
     args = parser.parse_args()
@@ -77,89 +79,87 @@ def main():
     try:
         load_config(args.reset_config)
     except FileNotFoundError as e:
-        print(f'Error: Failed to load config: {e}')
+        print(f'Error: Failed to load configuration file: {e}')
         return
 
-    if args.merge:
-        field = args.merge
-        num_files = len(args.filenames)
-
-        if num_files != 3:
-            print('Error: Argument -m/--merge requires three file arguments')
-            return
-
-        file_format, df1, num_valid_rows1, num_invalid_rows = read_data(args.filenames[0])
-        file_format, df2, num_valid_rows2, num_invalid_rows = read_data(args.filenames[1])
-
-        if num_valid_rows1 <= 0 or num_valid_rows2 <= 0:
-            print('Error: At least one of the input files is unsupported')
-            return
-
-        temp_df = df1[['co2']]
-        df2 = pd.concat([df2, temp_df]).sort_index()
-        df2.to_csv(args.filenames[2], index=True)
+    filenames = []
 
+    if sys.platform == "win32":
+        # On Windows, expand glob patterns (e.g. *.csv)
+        for pattern in args.filenames:
+            filenames.extend(glob.glob(pattern))
     else:
-        filenames = []
+        # On Linux, use filenames as-is (no glob expansion needed)
+        filenames = args.filenames
 
-        if sys.platform == "win32":
-            # On Windows, expand glob patterns (e.g. *.csv)
-            for pattern in args.filenames:
-                filenames.extend(glob.glob(pattern))
-        else:
-            # On Linux, use filenames as-is (no glob expansion needed)
-            filenames = args.filenames
+    if args.merge:
+        # Merge field from file1 to file2, and output to file3
+        merge_field(args.merge, filenames)
 
-        for filename in filenames:
-            print(f'Processing {filename}')
-            try:
-                file_format, df, num_valid_rows, num_invalid_rows = read_data(filename)
+    elif args.snapshots:
+        # Generate a snapshots table from all files
+        generate_snapshots(filenames)
 
-                if num_valid_rows > 0:
-                    logger.debug(f'{num_valid_rows} valid row(s) read')
-                else:
-                    print('Error: Unsupported file format')
-                    return
-
-                if num_invalid_rows > 0:
-                    percent_ignored = round(num_invalid_rows / (num_valid_rows + num_invalid_rows) * 100)
-                    print(f'{num_invalid_rows} invalid row(s) ignored ({percent_ignored}%)')
-
-                if not args.all_dates:
-                    df = delete_old_data(df, args.start_date, args.stop_date)
-
-                generate_stats(df, filename, args.boxplot)
-
-                if file_format == 'plotair':
-                    generate_plot(df, filename, args.title, suffix='cht',
-                             series1='co2', series2='humidity', series3='temp',
-                             filter_outliers=args.filter_outliers,
-                             filter_multiplier=args.filter_multiplier)
-                elif file_format == 'visiblair_d':
-                    generate_plot(df, filename, args.title, suffix='cht',
-                             series1='co2', series2='humidity', series3='temp',
-                             filter_outliers=args.filter_outliers,
-                             filter_multiplier=args.filter_multiplier)
-                elif file_format == 'visiblair_e':
-                    generate_plot(df, filename, args.title, suffix='cht',
-                             series1='co2', series2='humidity', series3='temp',
-                             filter_outliers=args.filter_outliers,
-                             filter_multiplier=args.filter_multiplier)
-                    generate_plot(df, filename, args.title, suffix='pm',
-                             series1=None, series2='pm2.5', series3='pm10',
-                             filter_outliers=args.filter_outliers,
-                             filter_multiplier=args.filter_multiplier)
-                elif file_format == 'graywolf_ds':
-                    generate_plot(df, filename, args.title, suffix='ht',
-                             series1=None, series2='humidity', series3='temp',
-                             filter_outliers=args.filter_outliers,
-                             filter_multiplier=args.filter_multiplier)
-                    generate_plot(df, filename, args.title, suffix='vcf',
-                             series1='tvoc', series2='form', series3='co',
-                             filter_outliers=args.filter_outliers,
-                             filter_multiplier=args.filter_multiplier)
-            except Exception as e:
-                print(f'Error: Unexpected error: {e}')
+    else:
+        # Generate plots for all files
+        process_files(filenames, args)
+
+
+def process_files(filenames, args):
+    for filename in filenames:
+        print(f'Processing {filename}')
+        try:
+            file_format, df, num_valid_rows, num_invalid_rows = read_data(filename)
+
+            if num_valid_rows > 0:
+                logger.debug(f'{num_valid_rows} valid row(s) read')
+            else:
+                print('Error: Unsupported file format')
+                return
+
+            if num_invalid_rows > 0:
+                percent_ignored = round(num_invalid_rows / (num_valid_rows + num_invalid_rows) * 100)
+                print(f'{num_invalid_rows} invalid row(s) ignored ({percent_ignored}%)')
+
+            if not args.all_dates:
+                df = delete_old_data(df, args.start_date, args.stop_date)
+
+            generate_stats(df, filename, args.boxplot)
+
+            if file_format == 'plotair':
+                generate_plot(df, filename, args.title, suffix='cht',
+                         series1='co2', series2='humidity', series3='temp',
+                         filter_outliers=args.filter_outliers,
+                         filter_multiplier=args.filter_multiplier)
+            elif file_format == 'visiblair_d':
+                generate_plot(df, filename, args.title, suffix='cht',
+                         series1='co2', series2='humidity', series3='temp',
+                         filter_outliers=args.filter_outliers,
+                         filter_multiplier=args.filter_multiplier)
+            elif file_format == 'visiblair_e':
+                generate_plot(df, filename, args.title, suffix='cht',
+                         series1='co2', series2='humidity', series3='temp',
+                         filter_outliers=args.filter_outliers,
+                         filter_multiplier=args.filter_multiplier)
+                generate_plot(df, filename, args.title, suffix='pm',
+                         series1=None, series2='pm2.5', series3='pm10',
+                         filter_outliers=args.filter_outliers,
+                         filter_multiplier=args.filter_multiplier)
+            elif file_format == 'graywolf_ds':
+                generate_plot(df, filename, args.title, suffix='ht',
+                         series1=None, series2='humidity', series3='temp',
+                         filter_outliers=args.filter_outliers,
+                         filter_multiplier=args.filter_multiplier)
+                generate_plot(df, filename, args.title, suffix='vf',
+                         series1='tvoc', series2='form', series3=None,
+                         filter_outliers=args.filter_outliers,
+                         filter_multiplier=args.filter_multiplier)
+                generate_plot(df, filename, args.title, suffix='co',
+                         series1=None, series2='co', series3=None,
+                         filter_outliers=args.filter_outliers,
+                         filter_multiplier=args.filter_multiplier)
+        except Exception as e:
+            print(f'Error: Unexpected error: {e}')
 
 
 def detect_file_format(filename):
@@ -186,9 +186,9 @@ def detect_file_format(filename):
         elif (graywolf_ds_num_col[0] <= num_fields <= graywolf_ds_num_col[1] and
               first_line[0] == 'Date Time'):
             file_format = 'graywolf_ds'
-        
+
     logger.debug(f'File format: {file_format}')
-    
+
     return file_format
 
 
@@ -240,13 +240,13 @@ def read_data_visiblair_d(filename):
         for line in f:
             line = line.strip()
             fields = line.split(',')
-            
+
             if not (5 <= len(fields) <= 6):
                 # Skip lines with an invalid number of columns
                 #logger.debug(f'Skipping line (number of columns): {line}')
                 num_invalid_rows += 1
                 continue
-                
+
             try:
                 # Convert each field to its target data type
                 parsed_row = {
@@ -257,7 +257,7 @@ def read_data_visiblair_d(filename):
                 }
                 # If conversion succeeds, add the parsed row to the list
                 valid_rows.append(parsed_row)
-                
+
             except (ValueError, TypeError) as e:
                 # Skip lines with conversion errors
                 #logger.debug(f'Skipping line (conversion error): {line}')
@@ -307,7 +307,8 @@ def read_data_graywolf_ds(filename):
     # Convert the 'date' column to pandas datetime objects
     df['date'] = pd.to_datetime(df['date'], format='%d-%b-%y %I:%M:%S %p')
 
-    # Convert 'form' column to string, replace '< LOD' with '0', and then convert to integer
+    # Convert 'form' column to string, replace '< LOD' with '10',
+    # and then convert to integer
     df['form'] = df['form'].astype(str).str.replace('< LOD', '10').astype(int)
 
     df = df.set_index('date')
@@ -316,6 +317,25 @@ def read_data_graywolf_ds(filename):
     return df, num_valid_rows, num_invalid_rows
 
 
+def merge_field(field, filenames):
+    num_files = len(filenames)
+
+    if num_files != 3:
+        print('Error: Argument -m/--merge requires three file arguments')
+        return
+
+    file_format, df1, num_valid_rows1, num_invalid_rows = read_data(filenames[0])
+    file_format, df2, num_valid_rows2, num_invalid_rows = read_data(filenames[1])
+
+    if num_valid_rows1 <= 0 or num_valid_rows2 <= 0:
+        print('Error: At least one of the input files is unsupported')
+        return
+
+    temp_df = df1[[field]]
+    df2 = pd.concat([df2, temp_df]).sort_index()
+    df2.to_csv(filenames[2], index=True)
+
+
 def delete_old_data(df, start_date = None, stop_date = None):
     if not start_date and not stop_date:
         # Iterate backwards through the samples to find the first time gap larger
@@ -349,7 +369,7 @@ def delete_old_data(df, start_date = None, stop_date = None):
             df = df[df.index <= sd]
 
     return df
-    
+
 
 class DataSeries:
     def __init__(self, name=''):
@@ -368,12 +388,12 @@ def generate_plot(df, filename, title, suffix='',
                   filter_outliers=False, filter_multiplier=None):
     # The dates must be in a non-index column
     df = df.reset_index()
-    
+
     # Get each series configuration
     ds1 = DataSeries(name=series1) if series1 else None
     ds2 = DataSeries(name=series2) if series2 else None
     ds3 = DataSeries(name=series3) if series3 else None
-    
+
     # Set a theme and scale all fonts
     sns.set_theme(style='whitegrid', font_scale=CONFIG['plot']['font_scale'])
 
@@ -386,7 +406,7 @@ def generate_plot(df, filename, title, suffix='',
 
     # TODO: add functions for repetitive code
 
-    # Plot series #1 main line
+    # Plot series #1 main line (on left y-axis)
     if ds1:
         if ds1.linestyle:
             linestyle = ds1.linestyle
@@ -414,7 +434,7 @@ def generate_plot(df, filename, title, suffix='',
             ax1.axhspan(ymin=hmin, ymax=hmax, facecolor=ds1.color,
                         alpha=CONFIG['plot']['limit_zone_opacity'])
 
-    # Plot series #2 main line
+    # Plot series #2 main line (on right y-axis)
     if ds2.linestyle:
         linestyle = ds2.linestyle
     else:
@@ -441,36 +461,33 @@ def generate_plot(df, filename, title, suffix='',
         ax2.axhspan(ymin=hmin, ymax=hmax, facecolor=ds2.color,
                     alpha=CONFIG['plot']['limit_zone_opacity'])
 
-    # Plot series #3 main line
-    if ds3.linestyle:
-        linestyle = ds3.linestyle
-    else:
-        linestyle = CONFIG['plot']['default_line_style']
-
-    # TODO: Do we still want to scale the CO data series?
-    #co_scale = 10
-    #df['co_scaled'] = df['co'] * co_scale
+    # Plot series #3 main line (on right y-axis)
+    if ds3:
+        if ds3.linestyle:
+            linestyle = ds3.linestyle
+        else:
+            linestyle = CONFIG['plot']['default_line_style']
 
-    if filter_outliers:
-        df3 = remove_outliers_iqr(df, ds3.name, multiplier=filter_multiplier)
-    else:
-        df3 = df[df[ds3.name] != 0]  # Only filter out zero values
+        if filter_outliers:
+            df3 = remove_outliers_iqr(df, ds3.name, multiplier=filter_multiplier)
+        else:
+            df3 = df[df[ds3.name] != 0]  # Only filter out zero values
 
-    sns.lineplot(data=df3, x='date', y=ds3.name, ax=ax2, color=ds3.color,
-                 label=ds3.label, legend=False, linestyle=linestyle)
+        sns.lineplot(data=df3, x='date', y=ds3.name, ax=ax2, color=ds3.color,
+                     label=ds3.label, legend=False, linestyle=linestyle)
 
-    # Plot series #3 limit line
-    if ds3.limit and not isinstance(ds3.limit, list):
-        # Plot the limit line
-        line = ax2.axhline(y=ds3.limit, color=ds3.color, label=ds3.limit_label,
-                           linestyle=CONFIG['plot']['limit_line_style'])
-        line.set_alpha(CONFIG['plot']['limit_line_opacity'])
+        # Plot series #3 limit line
+        if ds3.limit and not isinstance(ds3.limit, list):
+            # Plot the limit line
+            line = ax2.axhline(y=ds3.limit, color=ds3.color, label=ds3.limit_label,
+                               linestyle=CONFIG['plot']['limit_line_style'])
+            line.set_alpha(CONFIG['plot']['limit_line_opacity'])
 
-    if ds3.limit and isinstance(ds3.limit, list):
-        # Set the background color of the limit zone
-        hmin, hmax = ds3.limit
-        ax2.axhspan(ymin=hmin, ymax=hmax, facecolor=ds3.color,
-                    alpha=CONFIG['plot']['limit_zone_opacity'])
+        if ds3.limit and isinstance(ds3.limit, list):
+            # Set the background color of the limit zone
+            hmin, hmax = ds3.limit
+            ax2.axhspan(ymin=hmin, ymax=hmax, facecolor=ds3.color,
+                        alpha=CONFIG['plot']['limit_zone_opacity'])
 
     # Set the ranges for both y axes
     if ds1:
@@ -478,12 +495,17 @@ def generate_plot(df, filename, title, suffix='',
         ax1.set_ylim(y1min, y1max)
 
     y2min, y2max = ds2.y_range
-    y3min, y3max = ds3.y_range
 
-    if y2min != y3min or y2max != y3max:
-        print(f'Warning: Axis ranges differ for {series2} and {series3}, using largest range')
+    if ds3:
+        y3min, y3max = ds3.y_range
 
-    ax2.set_ylim(min(y2min, y3min), max(y2max, y3max))
+        if y2min != y3min or y2max != y3max:
+            print(f'Warning: Axis ranges differ for {series2} and {series3}, using largest range')
+
+        y2min = min(y2min, y3min)
+        y2max = max(y2max, y3max)
+
+    ax2.set_ylim(y2min, y2max)
 
     # Add a grid for the x axis and the y axes
     # This is already done if using the whitegrid theme
@@ -498,23 +520,28 @@ def generate_plot(df, filename, title, suffix='',
         ax1.tick_params(axis='y', labelcolor=ds1.color)
         ax1.set_ylabel(ds1.label, color=ds1.color)
     ax1.set_xlabel('')
-    ax2.set_ylabel('')  # We will manually place the 2 parts in different colors
 
-    # Define the position for the center of the right y axis label
-    bottom_label = ds3.label + '  '
-    top_label = '  ' + ds2.label
-    x = 1.07  # Slightly to the right of the axis
-    y = get_label_center(bottom_label, top_label)   # Vertically centered
+    if ds3:
+        ax2.set_ylabel('')  # We will manually place the 2 parts in different colors
 
-    # Place the first (bottom) part of the label
-    ax2.text(x, y, bottom_label, transform=ax2.transAxes,
-             color=ds3.color, rotation='vertical',
-             ha='center', va='top')
+        # Define the position for the center of the right y axis label
+        bottom_label = ds3.label + '  '
+        top_label = '  ' + ds2.label
+        x = 1.07  # Slightly to the right of the axis
+        y = get_label_center(bottom_label, top_label)   # Vertically centered
 
-    # Place the second (top) part of the label
-    ax2.text(x, y, top_label, transform=ax2.transAxes,
-            color=ds2.color, rotation='vertical',
-            ha='center', va='bottom')
+        # Place the first (bottom) part of the label
+        ax2.text(x, y, bottom_label, transform=ax2.transAxes,
+                 color=ds3.color, rotation='vertical',
+                 ha='center', va='top')
+
+        # Place the second (top) part of the label
+        ax2.text(x, y, top_label, transform=ax2.transAxes,
+                color=ds2.color, rotation='vertical',
+                ha='center', va='bottom')
+    else:
+        ax2.tick_params(axis='y', labelcolor=ds2.color)
+        ax2.set_ylabel(ds2.label, color=ds2.color)
 
     # Create a combined legend
     lines1, labels1 = ax1.get_legend_handles_labels()
@@ -539,6 +566,94 @@ def generate_plot(df, filename, title, suffix='',
     plt.close()
 
 
+def generate_snapshots(filenames):
+    columns = ['date', 'tvoc', 'co', 'form', 'humidity', 'temp', 'filename']
+    df = pd.DataFrame()
+
+    for filename in filenames:
+        print(f'Reading {filename}')
+
+        # Auto-detect field separator, skip the header row,
+        # and only read one data row
+        df_new = pd.read_csv(filename, sep=None, engine='python',
+                             names=columns, skiprows=1, nrows=1)
+
+        # Update the filename field with the actual filename
+        df_new['filename'] = Path(filename).stem
+
+        # Append to the combined DataFrame
+        if df.empty:
+            # Prevent a warning on the first concat
+            df = df_new
+        else:
+            df = pd.concat([df, df_new], ignore_index=True)
+
+    # Convert 'form' column to string, and replace '< LOD' with '<10'
+    df['form'] = df['form'].astype(str).str.replace('< LOD', '<10')
+
+    # Drop the 'date' column, and move last column (filename) to first
+    df = df.drop(columns=['date'])
+    df = df[[df.columns[-1]] + df.columns[:-1].tolist()]
+
+    # Capitalize only the first character of the filenames
+    df['filename'] = df['filename'].str.capitalize()
+
+    # Rename the columns before creating the table
+    # TODO: use config file values instead
+    # TODO: directly assign to `df.columns` to change all column names at once
+    df = df.rename(columns={'filename': 'Pièce'})
+    df = df.rename(columns={'tvoc': 'COVT (ppb)'})
+    df = df.rename(columns={'co': 'Monoxyde de\ncarbone (ppm)'})
+    df = df.rename(columns={'form': 'Formaldéhyde\n(ppb)'})
+    df = df.rename(columns={'humidity': 'Humidité\nrelative (%)'})
+    df = df.rename(columns={'temp': 'Température (°C)'})
+
+    #log_data_frame(df, filename)
+
+    # Create table
+    fig, ax = plt.subplots(figsize=(7, 4))
+    #ax.axis('tight')
+    ax.axis('off')
+    table = ax.table(cellText=df.values,
+                     colLabels=df.columns,
+                     cellLoc='center',
+                     loc='center')
+    table.auto_set_font_size(False)
+    table.set_fontsize(10)
+    table.scale(2, 2)  # column width, row height
+
+    # Change grid color and set alternating row colors
+    for i in range(len(df) + 1):  # +1 for header row
+        for j in range(len(df.columns)):
+            cell = table[(i, j)]
+            #cell.set_text_props(fontfamily='Noto Sans')
+            cell.set_edgecolor('#bbbbbb')      # Medium light gray
+
+            if i % 2 == 0:
+                cell.set_facecolor('#f4f4f4')  # Very light gray
+            else:
+                cell.set_facecolor('#ffffff')  # White
+
+    # Header row: increase height, make text bold, and add background color
+    for j in range(len(df.columns)):
+        cell = table[(0, j)]
+        cell.set_height(0.15)
+        cell.set_text_props(weight='bold')
+        cell.set_facecolor('#dddddd')          # Light gray
+
+    # First column: change alignment to left, except for the header
+    for i in range(1, len(df) + 1):
+        table[(i, 0)].set_text_props(ha='left')
+
+    plt.savefig(get_plot_filename(filename, stem='snapshots'),
+                bbox_inches='tight', dpi=300)
+    plt.close()
+
+    # Write a csv file to paste easily in a spreadsheet
+    df.columns = df.columns.str.replace('\n', ' ')
+    df.to_csv(get_filename(filenames[0], stem='snapshots', extension='txt'), index=False)
+    
+
 def remove_units_from_labels(labels):
     return [re.sub(r' \([^)]*\)', '', label) for label in labels]
 
@@ -547,18 +662,18 @@ def remove_outliers_iqr(df, column, multiplier=None):
     """
     Remove outliers using Interquartile Range (IQR) method
     multiplier = 1.0: Tight bounds, more outliers removed
-    multiplier = 1.5: Standard bounds, moderate outliers removed  
+    multiplier = 1.5: Standard bounds, moderate outliers removed
     multiplier = 2.0: Wide bounds, fewer outliers removed
     """
     if multiplier == None:
         multiplier = 1.5  # Default value
-        
+
     Q1 = df[column].quantile(0.25)
     Q3 = df[column].quantile(0.75)
     IQR = Q3 - Q1
     lower_bound = Q1 - multiplier * IQR
     upper_bound = Q3 + multiplier * IQR
-    
+
     return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)]
 
 
@@ -575,7 +690,7 @@ def remove_outliers_std(df, column, n_std=2):
     std = df[column].std()
     lower_bound = mean - n_std * std
     upper_bound = mean + n_std * std
-    
+
     return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)]
 
 
@@ -583,7 +698,7 @@ def remove_outliers_std(df, column, n_std=2):
 def remove_outliers_percentile(df, column, lower_percentile=5, upper_percentile=95):
     lower_bound = df[column].quantile(lower_percentile/100)
     upper_bound = df[column].quantile(upper_percentile/100)
-    
+
     return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)]
 
 
@@ -646,10 +761,10 @@ def get_config_dir(app_name):
             config_dir = Path(config_home) / app_name
         else:
             config_dir = Path.home() / ".config" / app_name
-    
+
     # Create the directory if it doesn't exist
     config_dir.mkdir(parents=True, exist_ok=True)
-    
+
     return config_dir
 
 
@@ -662,14 +777,21 @@ def get_plot_title(title, filename):
         plot_title = match.group(2) if match else stem
 
     # Capitalize only the first character
-    if plot_title: plot_title = plot_title[0].upper() + plot_title[1:]
+    if plot_title: plot_title = plot_title.capitalize()
 
     return plot_title
 
 
-def get_plot_filename(filename, suffix = ''):
+def get_filename(filename, stem = '', suffix = '', extension = ''):
     p = Path(filename)
-    return f'{p.parent}/{p.stem}{suffix}.png'
+    s = stem if stem != '' else p.stem
+    return f'{p.parent}/{s}{suffix}.{extension}'
+
+
+def get_plot_filename(filename, suffix = '', stem = ''):
+    p = Path(filename)
+    s = stem if stem != '' else p.stem
+    return f'{p.parent}/{s}{suffix}.png'
 
 
 def get_boxplot_filename(filename, suffix = ''):
@@ -696,7 +818,7 @@ if __name__ == '__main__':
     # Configure the root logger
     logging.basicConfig(level=logging.WARNING,
                         format='%(levelname)s - %(message)s')
-    
+
     # Configure this script's logger
     logger.setLevel(logging.DEBUG)
 

plotair-0.2.1/plotair/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.2.1"