Fixes for the long term logs

    return concat_df

def plot_data(df, output_filename):

def plot_data(df, output_filename, days):

    """plot max values for 'MLD' and 'MAX_ABS_DIFF' data and save

    to html file."""

    # Convert 'date' to datetime

    df["MLD"] = pd.to_numeric(df["MLD"], errors="coerce")

    df["MAX_ABS_DIFF"] = pd.to_numeric(df["MAX_ABS_DIFF"], errors="coerce")

    # Filter out rows older than "days"

    cutoff = df["date"].max() - pd.Timedelta(days=days)

    df = df[df["date"] > cutoff].reset_index(drop=True)

    # Drop rows with NaT and NaN

    clean_df = df.dropna(subset=["date", "MLD", "MAX_ABS_DIFF"])

    df = df.dropna(subset=["date", "MLD", "MAX_ABS_DIFF"])

    # Group by 'format' and 'date' to get rows with max 'MLD' per group

    max_mld = (

        clean_df.groupby(["format", "date"])

        .apply(lambda x: x.loc[x["MLD"].idxmax()])

        .reset_index(drop=True)

    )

    # Group by 'format' and 'date' to get rows with max 'MAX_ABS_DIFF' per

    # group

    max_abs_diff = (

        clean_df.groupby(["format", "date"])

        .apply(lambda x: x.loc[x["MAX_ABS_DIFF"].idxmax()])

        .reset_index(drop=True)

    )

    idx = df.groupby(['format', 'date'])['MLD'].idxmax()

    max = df.loc[idx].reset_index(drop=True)

    idx = df.groupby(['format', 'date'])['MLD'].idxmin()

    min = df.loc[idx].reset_index(drop=True)

    mean = df.groupby(['format', 'date'])['MLD'].mean().to_frame('mean').reset_index()

    formats = sorted(clean_df["format"].unique())

    formats = sorted(df["format"].unique())

    fig = make_subplots(

        rows=5,

        cols=2,

        specs=[[{"secondary_y": True}] * 2] * 5,

        subplot_titles=[f"{i}" for i in formats],

        shared_xaxes="columns",

    )

        row = i // 2 + 1

        col = i % 2 + 1

        data_mld = max_mld[max_mld["format"] == fmt].sort_values("date")

        data_diff = max_abs_diff[max_abs_diff["format"]

                                 == fmt].sort_values("date")

        data_mld = max[max["format"] == fmt].sort_values("date")

        # Add max 'MLD' to primary y-axis

        fig.add_trace(

                x=data_mld["date"],

                y=data_mld["MLD"],

                mode="lines+markers",

                name=f" {fmt} - Max MLD",

                name=f"Max MLD",

                hovertext=[

                    f"Testcase: {tc}<br>MLD: {mld:.4f}<br>MAX_ABS_DIFF:"

                    f"{abs_diff}<br>Format:"

                    f"Testcase: {tc}<br>MLD: {mld:.4f}"

                    f" {format}<br>Date: {date.date()}"

                    for tc, mld, abs_diff, format, date in zip(

                    for tc, mld, format, date in zip(

                        data_mld["testcase"],

                        data_mld["MLD"],

                        data_mld["MAX_ABS_DIFF"],

                        data_mld["format"],

                        data_mld["date"],

                    )

                ],

                hoverinfo="text",

            ),

            row=row,

            col=col,

            secondary_y=False,

        )

        # Add max 'MAX_ABS_DIFF' to secondary y-axis

        data_mld = mean[mean["format"] == fmt].sort_values("date")

        # Add mean 'MLD' to primary y-axis

        fig.add_trace(

            go.Scatter(

                x=data_diff["date"],

                y=data_diff["MAX_ABS_DIFF"],

                x=data_mld["date"],

                y=data_mld["mean"],

                mode="lines+markers",

                name=f"{fmt} - Max MAX_ABS_DIFF",

                name=f"Mean MLD",

                hovertext=[

                    f"Testcase: {tc}<br>MLD: {mld:.4f}<br>MAX_ABS_DIFF:"

                    f" {abs_diff:.4f}<br>Format:"

                    f"Mean MLD: {mld:.4f}"

                    f" {format}<br>Date: {date.date()}"

                    for tc, mld, abs_diff, format, date in zip(

                        data_diff["testcase"],

                        data_diff["MLD"],

                        data_diff["MAX_ABS_DIFF"],

                        data_diff["format"],

                        data_diff["date"],

                    for mld, format, date in zip(

                        data_mld["mean"],

                        data_mld["format"],

                        data_mld["date"],

                    )

                ],

                hoverinfo="text",

            ),

            row=row,

            col=col,

            secondary_y=True,

        )

    fig.update_layout(

        title_text="Long-term regression: max MLD and max MAX_ABS_DIFF",

        title_text="History: MLD",        

        legend=dict(x=1, y=1, orientation="v"),

        hovermode="x unified",

    )

    fig.update_xaxes(automargin=True)

    fig.update_yaxes(automargin=True)

    # Update y-axes titles per subplot

    for i in range(10):

        yaxis_num = i * 2 + 1

        yaxis2_num = yaxis_num + 1

        fig["layout"][f"yaxis{yaxis_num}"].update(

            title="Max MLD", titlefont=dict(color="blue"), tickfont=dict(color="blue")

        )

        fig["layout"][f"yaxis{yaxis2_num}"].update(

            title="Max MAX_ABS_DIFF",

            titlefont=dict(color="green"),

            tickfont=dict(color="green"),

        )

    # Save to html

    fig.write_html(output_filename)

        type=str,

        help="Filename of the generated plot. e.g" ". long_term_regression.html",

    )

    parser.add_argument(

        "--days",

        type=int,

        help="Number of days in history. Default: 30",

        default=30,

    )    

    args = parser.parse_args()

    csv_data = read_csv_files(args.root_dir)

    data = parse_csv_data(csv_data)

    plot_data(data, args.output_filename)

    plot_data(data, args.output_filename, args.days)