plotair 0.2.0__py3-none-any.whl → 0.3.0__py3-none-any.whl

plotair/main.py

@@ -53,8 +53,14 @@ def main():
                         help='sensor data file to process')
     parser.add_argument('-a', '--all-dates', action='store_true',
                         help='plot all dates (otherwise only latest sequence)')
+    parser.add_argument('-b', '--boxplot', action='store_true',
+                        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('-r', '--reset-config', action='store_true',
                         help='reset configuration file to default')
     parser.add_argument('-s', '--start-date', metavar='DATE',
@@ -63,7 +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()
@@ -71,66 +79,87 @@ def main():
     try:
         load_config(args.reset_config)
     except FileNotFoundError as e:
-        logger.error(f'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:
-            logger.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])
+    filenames = []
 
-        if num_valid_rows1 <= 0 or num_valid_rows2 <= 0:
-            logger.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)
-
-    else:
-        # Create a list containing all files from all patterns like '*.csv',
-        # because under Windows the terminal doesn't expand wildcard arguments.
-        all_files = []
+    if sys.platform == "win32":
+        # On Windows, expand glob patterns (e.g. *.csv)
         for pattern in args.filenames:
-            all_files.extend(glob.glob(pattern))
-
-        for filename in all_files:
-            logger.info(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} row(s) read')
-                else:
-                    logger.error('Unsupported file format')
-                    return
-
-                if num_invalid_rows > 0:
-                    logger.info(f'{num_invalid_rows} invalid row(s) ignored')
+            filenames.extend(glob.glob(pattern))
+    else:
+        # On Linux, use filenames as-is (no glob expansion needed)
+        filenames = args.filenames
 
-                if not args.all_dates:
-                    df = delete_old_data(df, args.start_date, args.stop_date)
+    if args.merge:
+        # Merge field from file1 to file2, and output to file3
+        merge_field(args.merge, filenames)
 
-                generate_stats(df, filename)
+    elif args.snapshots:
+        # Generate a snapshots table from all files
+        generate_snapshots(filenames)
 
-                if file_format == 'plotair':
-                    generate_plot_co2_hum_tmp(df, filename, args.title)
-                elif file_format == 'visiblair_d':
-                    generate_plot_co2_hum_tmp(df, filename, args.title)
-                elif file_format == 'visiblair_e':
-                    generate_plot_co2_hum_tmp(df, filename, args.title)
-                    generate_plot_pm(df, filename, args.title)
-                elif file_format == 'graywolf_ds':
-                    generate_plot_hum_tmp(df, filename, args.title)
-                    generate_plot_voc_co_form(df, filename, args.title)
-            except Exception as e:
-                logger.exception(f'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):
@@ -139,11 +168,14 @@ def detect_file_format(filename):
     visiblair_e_num_col = (21, 21)
     graywolf_ds_num_col = (7, 7)
 
-    with open(filename, 'r', newline='', encoding='utf-8') as file:
+    # Some files begin with the '\ufeff' character (Byte Order Mark / BOM).
+    # This breaks the first field detection. Use 'utf-8-sig' instead of 'utf-8'
+    # to automatically handle BOM.
+    with open(filename, 'r', newline='', encoding='utf-8-sig') as file:
         reader = csv.reader(file)
         first_line = next(reader)
         num_fields = len(first_line)
-        
+
         if first_line[0] == 'date':
             file_format = 'plotair'
         elif visiblair_d_num_col[0] <= num_fields <= visiblair_d_num_col[1]:
@@ -154,9 +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
 
 
@@ -175,6 +207,8 @@ def read_data(filename):
     elif file_format == 'graywolf_ds':
         df, num_valid_rows, num_invalid_rows = read_data_graywolf_ds(filename)
 
+    df = df.sort_index()  # Sort in case some dates are not in order
+
     return file_format, df, num_valid_rows, num_invalid_rows
 
 
@@ -189,7 +223,6 @@ def read_data_plotair(filename):
     df['date'] = pd.to_datetime(df['date'], format='%Y-%m-%d %H:%M:%S')
 
     df = df.set_index('date')
-    df = df.sort_index()  # Sort in case some dates are not in order
     num_valid_rows = len(df)
 
     return df, num_valid_rows, num_invalid_rows
@@ -207,34 +240,33 @@ 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}')
+                #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 = {
                     'date': pd.to_datetime(fields[0], format='%Y-%m-%d %H:%M:%S'),
-                    'co2': np.uint16(fields[1]),           # 0 to 10,000 ppm
-                    'temperature': np.float32(fields[2]),  # -40 to 70 °C
-                    'humidity': np.uint8(fields[3])        # 0 to 100% RH
+                    'co2': np.uint16(fields[1]),     # 0 to 10,000 ppm
+                    'temp': np.float32(fields[2]),   # -40 to 70 °C
+                    'humidity': np.uint8(fields[3])  # 0 to 100% RH
                 }
                 # 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}')
+                #logger.debug(f'Skipping line (conversion error): {line}')
                 num_invalid_rows += 1
                 continue
 
         # Create the DataFrame from the valid rows
         df = pd.DataFrame(valid_rows)
         df = df.set_index('date')
-        df = df.sort_index()  # Sort in case some dates are not in order
         num_valid_rows = len(df)
 
     return df, num_valid_rows, num_invalid_rows
@@ -248,7 +280,7 @@ def read_data_visiblair_e(filename):
     df = pd.read_csv(filename)
 
     # Rename the columns
-    df.columns = ['uuid', 'date', 'co2', 'humidity', 'temperature', 'pm0.1',
+    df.columns = ['uuid', 'date', 'co2', 'humidity', 'temp', 'pm0.1',
                   'pm0.3', 'pm0.5', 'pm1', 'pm2.5', 'pm5', 'pm10', 'pressure',
                   'voc_index', 'firmware', 'model', 'pcb', 'display_rate',
                   'is_charging', 'is_ac_in', 'batt_voltage']
@@ -257,7 +289,6 @@ def read_data_visiblair_e(filename):
     df['date'] = pd.to_datetime(df['date'], format='%Y-%m-%d %H:%M:%S')
 
     df = df.set_index('date')
-    df = df.sort_index()  # Sort in case some dates are not in order
     num_valid_rows = len(df)
 
     return df, num_valid_rows, num_invalid_rows
@@ -271,21 +302,40 @@ def read_data_graywolf_ds(filename):
     df = pd.read_csv(filename)
 
     # Rename the columns
-    df.columns = ['date', 'tvoc', 'co', 'form', 'humidity', 'temperature', 'filename']
+    df.columns = ['date', 'tvoc', 'co', 'form', 'humidity', 'temp', '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
-    df['form'] = df['form'].astype(str).str.replace('< LOD', '0').astype(int)
+    # 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')
-    df = df.sort_index()  # Sort in case some dates are not in order
     num_valid_rows = len(df)
 
     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
@@ -319,12 +369,31 @@ def delete_old_data(df, start_date = None, stop_date = None):
             df = df[df.index <= sd]
 
     return df
-    
 
-def generate_plot_co2_hum_tmp(df, filename, title):
+
+class DataSeries:
+    def __init__(self, name=''):
+        # y_range could be replaced by y_min and y_max
+        self.name = name
+        self.label = CONFIG['labels'].get(self.name)
+        self.color = CONFIG['colors'].get(self.name)
+        self.y_range = CONFIG['axis_ranges'].get(self.name)  # min/max tuple, e.g. (0, 100)
+        self.limit = CONFIG['limits'].get(self.name)  # single value or min/max tuple
+        self.limit_label = CONFIG['labels'].get(self.name + '_limit')
+        self.linestyle = CONFIG['plot'].get(self.name + '_line_style')
+
+
+def generate_plot(df, filename, title, suffix='',
+                  series1=None, series2=None, series3=None,
+                  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'])
 
@@ -335,96 +404,108 @@ def generate_plot_co2_hum_tmp(df, filename, title):
     fig, ax1 = plt.subplots(figsize=CONFIG['plot']['size'])
     ax2 = ax1.twinx()  # Secondary y axis
 
-    # Plot the data series
-    sns.lineplot(data=df, x='date', y='co2', ax=ax1, color=CONFIG['colors']['co2'],
-                 label=CONFIG['labels']['co2'], legend=False)
-    sns.lineplot(data=df, x='date', y='humidity', ax=ax2, color=CONFIG['colors']['humidity'],
-                 label=CONFIG['labels']['humidity'], legend=False)
-    sns.lineplot(data=df, x='date', y='temperature', ax=ax2, color=CONFIG['colors']['temp'],
-                 label=CONFIG['labels']['temp'], legend=False)
+    # TODO: add functions for repetitive code
 
-    # Set the ranges for both y axes
-    cmin, cmax = CONFIG['axis_ranges']['co2']
-    tmin, tmax = CONFIG['axis_ranges']['temp_h']
-    ax1.set_ylim(cmin, cmax)  # df['co2'].max() * 1.05
-    ax2.set_ylim(tmin, tmax)
-
-    # Add a grid for the x axis and the y axes
-    # This is already done if using the whitegrid theme
-    #ax1.grid(axis='x', alpha=CONFIG['plot']['grid_opacity'])
-    #ax1.grid(axis='y', alpha=CONFIG['plot']['grid_opacity'])
-    ax2.grid(axis='y', alpha=CONFIG['plot']['grid2_opacity'], linestyle=CONFIG['plot']['grid2_line_style'])
-
-    # Set the background color of the humidity comfort zone
-    hmin, hmax = CONFIG['limits']['humidity']
-    ax2.axhspan(ymin=hmin, ymax=hmax,
-                facecolor=CONFIG['colors']['humidity'], alpha=CONFIG['plot']['limit_zone_opacity'])
-
-    # Customize the plot title, labels and ticks
-    ax1.set_title(get_plot_title(title, filename))
-    ax1.tick_params(axis='x', rotation=CONFIG['plot']['date_rotation'])
-    ax1.tick_params(axis='y', labelcolor=CONFIG['colors']['co2'])
-    ax1.set_xlabel('')
-    ax1.set_ylabel(CONFIG['labels']['co2'], color=CONFIG['colors']['co2'])
-    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 = CONFIG['labels']['temp'] + '  '
-    top_label = '  ' + CONFIG['labels']['humidity']
-    x = 1.07  # Slightly to the right of the axis
-    y = get_label_center(bottom_label, top_label)   # Vertically centered
+    # Plot series #1 main line (on left y-axis)
+    if ds1:
+        if ds1.linestyle:
+            linestyle = ds1.linestyle
+        else:
+            linestyle = CONFIG['plot']['default_line_style']
 
-    # Place the first (bottom) part of the label
-    ax2.text(x, y, bottom_label, transform=ax2.transAxes,
-             color=CONFIG['colors']['temp'], rotation='vertical',
-             ha='center', va='top')
+        if filter_outliers:
+            df1 = remove_outliers_iqr(df, ds1.name, multiplier=filter_multiplier)
+        else:
+            df1 = df[df[ds1.name] != 0]  # Only filter out zero values
+
+        sns.lineplot(data=df1, x='date', y=ds1.name, ax=ax1, color=ds1.color,
+                     label=ds1.label, legend=False, linestyle=linestyle)
+
+        # Display series #1 limit line or zone
+        if ds1.limit and not isinstance(ds1.limit, list):
+            # Plot the limit line
+            line = ax1.axhline(y=ds1.limit, color=ds1.color, label=ds1.limit_label,
+                               linestyle=CONFIG['plot']['limit_line_style'])
+            line.set_alpha(CONFIG['plot']['limit_line_opacity'])
+
+        if ds1.limit and isinstance(ds1.limit, list):
+            # Set the background color of the limit zone
+            hmin, hmax = ds1.limit
+            ax1.axhspan(ymin=hmin, ymax=hmax, facecolor=ds1.color,
+                        alpha=CONFIG['plot']['limit_zone_opacity'])
+
+    # Plot series #2 main line (on right y-axis)
+    if ds2.linestyle:
+        linestyle = ds2.linestyle
+    else:
+        linestyle = CONFIG['plot']['default_line_style']
 
-    # Place the second (top) part of the label
-    ax2.text(x, y, top_label, transform=ax2.transAxes,
-            color=CONFIG['colors']['humidity'], rotation='vertical',
-            ha='center', va='bottom')
+    if filter_outliers:
+        df2 = remove_outliers_iqr(df, ds2.name, multiplier=filter_multiplier)
+    else:
+        df2 = df[df[ds2.name] != 0]  # Only filter out zero values
+
+    sns.lineplot(data=df2, x='date', y=ds2.name, ax=ax2, color=ds2.color,
+                 label=ds2.label, legend=False, linestyle=linestyle)
+
+    # Display series #2 limit line or zone
+    if ds2.limit and not isinstance(ds2.limit, list):
+        # Plot the limit line
+        line = ax2.axhline(y=ds2.limit, color=ds2.color, label=ds2.limit_label,
+                           linestyle=CONFIG['plot']['limit_line_style'])
+        line.set_alpha(CONFIG['plot']['limit_line_opacity'])
+
+    if ds2.limit and isinstance(ds2.limit, list):
+        # Set the background color of the limit zone
+        hmin, hmax = ds2.limit
+        ax2.axhspan(ymin=hmin, ymax=hmax, facecolor=ds2.color,
+                    alpha=CONFIG['plot']['limit_zone_opacity'])
+
+    # Plot series #3 main line (on right y-axis)
+    if ds3:
+        if ds3.linestyle:
+            linestyle = ds3.linestyle
+        else:
+            linestyle = CONFIG['plot']['default_line_style']
 
-    # Create a combined legend
-    lines1, labels1 = ax1.get_legend_handles_labels()
-    lines2, labels2 = ax2.get_legend_handles_labels()
-    ax1.legend(lines1 + lines2, labels1 + labels2,
-               loc=CONFIG['plot']['legend_location'])
+        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
 
-    # Adjust the plot margins to make room for the labels
-    plt.tight_layout()
+        sns.lineplot(data=df3, x='date', y=ds3.name, ax=ax2, color=ds3.color,
+                     label=ds3.label, legend=False, linestyle=linestyle)
 
-    # Save the plot as a PNG image
-    plt.savefig(get_plot_filename(filename, '-cht'))
-    plt.close()
+        # 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'])
 
-def generate_plot_hum_tmp(df, filename, title):
-    # The dates must be in a non-index column
-    df = df.reset_index()
+    # Set the ranges for both y axes
+    if ds1:
+        y1min, y1max = ds1.y_range
+        ax1.set_ylim(y1min, y1max)
 
-    # Set a theme and scale all fonts
-    sns.set_theme(style='whitegrid', font_scale=CONFIG['plot']['font_scale'])
+    y2min, y2max = ds2.y_range
 
-    ff = CONFIG['plot']['font_family']
-    if ff != '': plt.rcParams['font.family'] = ff
+    if ds3:
+        y3min, y3max = ds3.y_range
 
-    # Set up the matplotlib figure and axes
-    fig, ax1 = plt.subplots(figsize=CONFIG['plot']['size'])
-    ax2 = ax1.twinx()  # Secondary y axis
+        if y2min != y3min or y2max != y3max:
+            print(f'Warning: Axis ranges differ for {series2} and {series3}, using largest range')
 
-    # Plot the data series
-    #sns.lineplot(data=df, x='date', y='co2', ax=ax1, color=CONFIG['colors']['co2'],
-    #             label=CONFIG['labels']['co2'], legend=False)
-    sns.lineplot(data=df, x='date', y='humidity', ax=ax2, color=CONFIG['colors']['humidity'],
-                 label=CONFIG['labels']['humidity'], legend=False)
-    sns.lineplot(data=df, x='date', y='temperature', ax=ax2, color=CONFIG['colors']['temp'],
-                 label=CONFIG['labels']['temp'], legend=False)
+        y2min = min(y2min, y3min)
+        y2max = max(y2max, y3max)
 
-    # Set the ranges for both y axes
-    cmin, cmax = CONFIG['axis_ranges']['co2']
-    tmin, tmax = CONFIG['axis_ranges']['temp_h']
-    ax1.set_ylim(cmin, cmax)  # df['co2'].max() * 1.05
-    ax2.set_ylim(tmin, tmax)
+    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
@@ -432,271 +513,215 @@ def generate_plot_hum_tmp(df, filename, title):
     #ax1.grid(axis='y', alpha=CONFIG['plot']['grid_opacity'])
     ax2.grid(axis='y', alpha=CONFIG['plot']['grid2_opacity'], linestyle=CONFIG['plot']['grid2_line_style'])
 
-    # Set the background color of the humidity comfort zone
-    hmin, hmax = CONFIG['limits']['humidity']
-    ax2.axhspan(ymin=hmin, ymax=hmax,
-                facecolor=CONFIG['colors']['humidity'], alpha=CONFIG['plot']['limit_zone_opacity'])
-
     # Customize the plot title, labels and ticks
     ax1.set_title(get_plot_title(title, filename))
     ax1.tick_params(axis='x', rotation=CONFIG['plot']['date_rotation'])
-    #ax1.tick_params(axis='y', labelcolor=CONFIG['colors']['co2'])
+    if ds1:
+        ax1.tick_params(axis='y', labelcolor=ds1.color)
+        ax1.set_ylabel(ds1.label, color=ds1.color)
     ax1.set_xlabel('')
-    #ax1.set_ylabel(CONFIG['labels']['co2'], color=CONFIG['colors']['co2'])
-    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 = CONFIG['labels']['temp'] + '  '
-    top_label = '  ' + CONFIG['labels']['humidity']
-    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=CONFIG['colors']['temp'], 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=CONFIG['colors']['humidity'], 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()
     lines2, labels2 = ax2.get_legend_handles_labels()
+    labels1 = remove_units_from_labels(labels1)
+    labels2 = remove_units_from_labels(labels2)
     ax1.legend(lines1 + lines2, labels1 + labels2,
                loc=CONFIG['plot']['legend_location'])
 
-    # Remove the left y-axis elements from ax1
-    ax1.grid(axis='y', visible=False)
-    ax1.spines['left'].set_visible(False)
-    ax1.tick_params(axis='y', left=False, labelleft=False)
+    if not ds1:
+        # Remove the left y-axis elements from ax1
+        ax1.grid(axis='y', visible=False)
+        ax1.spines['left'].set_visible(False)
+        ax1.tick_params(axis='y', left=False, labelleft=False)
 
     # Adjust the plot margins to make room for the labels
     plt.tight_layout()
 
     # Save the plot as a PNG image
-    plt.savefig(get_plot_filename(filename, '-ht'))
+    # TODO: auto build the plot suffix from the 1st char of each series?
+    plt.savefig(get_plot_filename(filename, f'-{suffix}'))
     plt.close()
 
 
-def generate_plot_voc_co_form(df, filename, title):
-    # The dates must be in a non-index column
-    df = df.reset_index()
-    
-    # Set a theme and scale all fonts
-    sns.set_theme(style='whitegrid', font_scale=CONFIG['plot']['font_scale'])
-
-    ff = CONFIG['plot']['font_family']
-    if ff != '': plt.rcParams['font.family'] = ff
-
-    # Set up the matplotlib figure and axes
-    fig, ax1 = plt.subplots(figsize=CONFIG['plot']['size'])
-    ax2 = ax1.twinx()  # Secondary y axis
-
-    # Plot the TVOC main line
-    sns.lineplot(data=df, x='date', y='tvoc', ax=ax1, legend=False,
-                 color=CONFIG['colors']['tvoc'], label=CONFIG['labels']['tvoc'])
-
-    # Plot the TVOC limit line
-    line = ax1.axhline(y=CONFIG['limits']['tvoc'], color=CONFIG['colors']['tvoc'],
-                linestyle=CONFIG['plot']['limit_line_style'], linewidth=CONFIG['plot']['limit_line_width'],
-                label=CONFIG['labels']['tvoc_limit'])
-    line.set_alpha(CONFIG['plot']['limit_line_opacity'])
-
-    # Plot the formaldehyde main line
-    df_filtered = df[df['form'] != 0]  # Filter out rows where 'form' is zero
-    sns.lineplot(data=df_filtered, x='date', y='form', ax=ax2, legend=False,
-                 color=CONFIG['colors']['form'], label=CONFIG['labels']['form'])
-
-    # Plot the formaldehyde limit line
-    line = ax2.axhline(y=CONFIG['limits']['form'], color=CONFIG['colors']['form'],
-                linestyle=CONFIG['plot']['limit_line_style'], linewidth=CONFIG['plot']['limit_line_width'],
-                label=CONFIG['labels']['form_limit'])
-    line.set_alpha(CONFIG['plot']['limit_line_opacity'])
-
-    # Plot the CO main line
-    co_scale = 10
-    df['co_scaled'] = df['co'] * co_scale
-    sns.lineplot(data=df, x='date', y='co_scaled', ax=ax2, legend=False,
-                 color=CONFIG['colors']['co'], label=CONFIG['labels']['co'])
-
-    # Plot the CO limit line
-    line = ax2.axhline(y=CONFIG['limits']['co'] * co_scale, color=CONFIG['colors']['co'],
-                linestyle=CONFIG['plot']['limit_line_style'], linewidth=CONFIG['plot']['limit_line_width'],
-                label=CONFIG['labels']['co_limit'])
-    line.set_alpha(CONFIG['plot']['limit_line_opacity'])
-
-    # Set the ranges for both y axes
-    tmin, tmax = CONFIG['axis_ranges']['tvoc']
-    cmin, cmax = CONFIG['axis_ranges']['co_form']
-    ax1.set_ylim(tmin, tmax)
-    ax2.set_ylim(cmin, cmax)
-
-    # Add a grid for the x axis and the y axes
-    # This is already done if using the whitegrid theme
-    #ax1.grid(axis='x', alpha=CONFIG['plot']['grid_opacity'])
-    #ax1.grid(axis='y', alpha=CONFIG['plot']['grid_opacity'])
-    ax2.grid(axis='y', alpha=CONFIG['plot']['grid2_opacity'], linestyle=CONFIG['plot']['grid2_line_style'])
-
-    # Customize the plot title, labels and ticks
-    ax1.set_title(get_plot_title(title, filename))
-    ax1.tick_params(axis='x', rotation=CONFIG['plot']['date_rotation'])
-    ax1.tick_params(axis='y', labelcolor=CONFIG['colors']['tvoc'])
-    ax1.set_xlabel('')
-    ax1.set_ylabel(CONFIG['labels']['tvoc'], color=CONFIG['colors']['tvoc'])
-    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 = CONFIG['labels']['co'] + '  '
-    top_label = '  ' + CONFIG['labels']['form']
-    x = 1.07  # Slightly to the right of the axis
-    y = get_label_center(bottom_label, top_label)   # Vertically centered
-
-    # Place the first (bottom) part of the label
-    ax2.text(x, y, bottom_label, transform=ax2.transAxes,
-             color=CONFIG['colors']['co'], rotation='vertical',
-             ha='center', va='top')
+def generate_snapshots(filenames):
+    columns = ['date', 'tvoc', 'co', 'form', 'humidity', 'temp', 'filename']
+    df = pd.DataFrame()
 
-    # Place the second (top) part of the label
-    ax2.text(x, y, top_label, transform=ax2.transAxes,
-             color=CONFIG['colors']['form'], rotation='vertical',
-             ha='center', va='bottom')
+    for filename in filenames:
+        print(f'Reading {filename}')
 
-    # Create a combined legend
-    lines1, labels1 = ax1.get_legend_handles_labels()
-    lines2, labels2 = ax2.get_legend_handles_labels()
-    ax1.legend(lines1 + lines2, labels1 + labels2,
-               loc=CONFIG['plot']['legend_location'])
+        # 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)
 
-    # Adjust the plot margins to make room for the labels
-    plt.tight_layout()
+        # Update the filename field with the actual filename
+        df_new['filename'] = Path(filename).stem
 
-    # Save the plot as a PNG image
-    plt.savefig(get_plot_filename(filename, '-vcf'))
+        # 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 generate_plot_pm(df, filename, title):
-    # The dates must be in a non-index column
-    df = df.reset_index()
-
-    # Set a theme and scale all fonts
-    sns.set_theme(style='whitegrid', font_scale=CONFIG['plot']['font_scale'])
-
-    ff = CONFIG['plot']['font_family']
-    if ff != '': plt.rcParams['font.family'] = ff
+def remove_units_from_labels(labels):
+    return [re.sub(r' \([^)]*\)', '', label) for label in labels]
 
-    # Set up the matplotlib figure and axes
-    fig, ax1 = plt.subplots(figsize=CONFIG['plot']['size'])
-    ax2 = ax1.twinx()  # Secondary y axis
 
-    #sns.lineplot(data=df, x='date', y='pm0.1', ax=ax1, color=CONFIG['colors']['pm0.1'],
-    #             label=CONFIG['labels']['pm0.1'], legend=False)
-
-    # Plot the PM2.5 main line
-    sns.lineplot(data=df, x='date', y='pm2.5', ax=ax2, legend=False,
-                 color=CONFIG['colors']['pm2.5'],
-                 label=CONFIG['labels']['pm2.5'],
-                 linewidth=CONFIG['plot']['pm2.5_line_width'],
-                 linestyle=CONFIG['plot']['pm2.5_line_style'])
-
-    # Plot the PM2.5 limit line
-    line = ax2.axhline(y=CONFIG['limits']['pm2.5'],
-                 color=CONFIG['colors']['pm2.5'],
-                 label=CONFIG['labels']['pm2.5_limit'],
-                 linewidth=CONFIG['plot']['limit_line_width'],
-                 linestyle=CONFIG['plot']['limit_line_style'])
-    line.set_alpha(CONFIG['plot']['limit_line_opacity'])
-
-    # Plot the PM10 main line
-    sns.lineplot(data=df, x='date', y='pm10', ax=ax2, legend=False,
-                 color=CONFIG['colors']['pm10'],
-                 label=CONFIG['labels']['pm10'],
-                 linewidth=CONFIG['plot']['pm10_line_width'],
-                 linestyle=CONFIG['plot']['pm10_line_style'])
-
-    # Plot the PM10 limit line
-    line = ax2.axhline(y=CONFIG['limits']['pm10'],
-                 color=CONFIG['colors']['pm10'],
-                 label=CONFIG['labels']['pm10_limit'],
-                 linewidth=CONFIG['plot']['limit_line_width'],
-                 linestyle=CONFIG['plot']['limit_line_style'])
-    line.set_alpha(CONFIG['plot']['limit_line_opacity'])
+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 = 2.0: Wide bounds, fewer outliers removed
+    """
+    if multiplier == None:
+        multiplier = 1.5  # Default value
 
-    # Set the ranges for both y axes
-    #min1, max1 = CONFIG['axis_ranges']['pm0.1']
-    min2, max2 = CONFIG['axis_ranges']['pm2.5_10']
-    #ax1.set_ylim(min1, max1)  # df['co2'].max() * 1.05
-    ax2.set_ylim(min2, max2)
+    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
 
-    # Add a grid for the x axis and the y axes
-    # This is already done if using the whitegrid theme
-    #ax1.grid(axis='x', alpha=CONFIG['plot']['grid_opacity'])
-    #ax1.grid(axis='y', alpha=CONFIG['plot']['grid_opacity'])
-    ax2.grid(axis='y', alpha=CONFIG['plot']['grid2_opacity'], linestyle=CONFIG['plot']['grid1_line_style'])
+    return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)]
 
-    # Customize the plot title, labels and ticks
-    ax1.set_title(get_plot_title(title, filename))
-    ax1.tick_params(axis='x', rotation=CONFIG['plot']['date_rotation'])
-    #ax1.tick_params(axis='y', labelcolor=CONFIG['colors']['pm0.1'])
-    ax1.set_xlabel('')
-    #ax1.set_ylabel(CONFIG['labels']['pm0.1'], color=CONFIG['colors']['pm0.1'])
-    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 = CONFIG['labels']['pm2.5'] + '  '
-    top_label = '  ' + CONFIG['labels']['pm10']
-    x = 1.07  # Slightly to the right of the axis
-    y = get_label_center(bottom_label, top_label)   # Vertically centered
+# WARNING: Untested function
+def remove_outliers_zscore(df, column, threshold=3):
+    # from scipy import stats ?
+    z_scores = np.abs(stats.zscore(df[column]))
+    return df[z_scores < threshold]
 
-    # Place the first (bottom) part of the label
-    ax2.text(x, y, bottom_label, transform=ax2.transAxes,
-             color=CONFIG['colors']['pm2.5'], rotation='vertical',
-             ha='center', va='top')
 
-    # Place the second (top) part of the label
-    ax2.text(x, y, top_label, transform=ax2.transAxes,
-            color=CONFIG['colors']['pm10'], rotation='vertical',
-            ha='center', va='bottom')
+# WARNING: Untested function
+def remove_outliers_std(df, column, n_std=2):
+    mean = df[column].mean()
+    std = df[column].std()
+    lower_bound = mean - n_std * std
+    upper_bound = mean + n_std * std
 
-    # Create a combined legend
-    lines1, labels1 = ax1.get_legend_handles_labels()
-    lines2, labels2 = ax2.get_legend_handles_labels()
-    ax1.legend(lines1 + lines2, labels1 + labels2,
-               loc=CONFIG['plot']['legend_location'])
+    return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)]
 
-    # Remove the left y-axis elements from ax1
-    ax1.grid(axis='y', visible=False)
-    ax1.spines['left'].set_visible(False)
-    ax1.tick_params(axis='y', left=False, labelleft=False)
 
-    # Adjust the plot margins to make room for the labels
-    plt.tight_layout()
+# WARNING: Untested function
+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)
 
-    # Save the plot as a PNG image
-    plt.savefig(get_plot_filename(filename, '-pm'))
-    plt.close()
+    return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)]
 
 
 def get_label_center(bottom_label, top_label):
     # Return a value between 0 and 1 to estimate where to center the label
+    # Divider optimized for 11x8.5 plot size, but not as good for 15x10
     fs = CONFIG['plot']['font_scale']
     divider = 72 * fs**2 - 316 * fs + 414  # Tested for fs between 0.8 and 2
     center = 0.5 + ((len(bottom_label) - len(top_label)) / divider)
     return center
 
 
-def generate_stats(df, filename):
+def generate_stats(df, filename, boxplot=False):
     summary = df.describe()
 
     with open(get_stats_filename(filename), 'w') as file:
         file.write(summary.to_string())
 
-    #for column in summary.columns.tolist():
-    #    box = sns.boxplot(data=df, y=column)
-    #    plt.savefig(get_boxplot_filename(filename, f'-{column}'))
-    #    plt.close()
+    if boxplot:
+        for column in summary.columns.tolist():
+            box = sns.boxplot(data=df, y=column)
+            plt.savefig(get_boxplot_filename(filename, f'-{column}'))
+            plt.close()
 
 
 def load_config(reset_config = False):
@@ -736,10 +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
 
 
@@ -752,19 +777,26 @@ 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)
+    s = stem if stem != '' else p.stem
+    return f'{p.parent}/{s}{suffix}.{extension}'
+
+
+def get_plot_filename(filename, suffix = '', stem = ''):
     p = Path(filename)
-    return f'{p.parent}/{p.stem}{suffix}.png'
+    s = stem if stem != '' else p.stem
+    return f'{p.parent}/{s}{suffix}.png'
 
 
-#def get_boxplot_filename(filename, suffix = ''):
-#    p = Path(filename)
-#    return f'{p.parent}/{p.stem}-boxplot{suffix}.png'
+def get_boxplot_filename(filename, suffix = ''):
+    p = Path(filename)
+    return f'{p.parent}/{p.stem}-boxplot{suffix}.png'
 
 
 def get_stats_filename(filename):
@@ -786,7 +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)