import os
import pandas as pd
import time
import json
from sklearn.metrics import precision_score, recall_score, f1_score
from utils.biz_utils import get_unique_words_text
from utils.logger import logger


class Metrics:
    def __init__(
        self,
        data_type: str,
        prediction_file: str,
        prediction_sheet_name: str = "Sheet1",
        ground_truth_file: str = None,
        ground_truth_sheet_name: str = "Sheet1",
        output_folder: str = None,
    ) -> None:
        self.data_type = data_type
        self.prediction_file = prediction_file
        self.prediction_sheet_name = prediction_sheet_name
        self.ground_truth_file = ground_truth_file
        self.ground_truth_sheet_name = ground_truth_sheet_name

        if output_folder is None or len(output_folder) == 0:
            output_folder = r"/data/emea_ar/output/metrics/"

        os.makedirs(output_folder, exist_ok=True)
        time_stamp = time.strftime("%Y%m%d%H%M%S", time.localtime())
        self.output_file = os.path.join(
            output_folder,
            f"metrics_{data_type}_{time_stamp}.xlsx",
        )

    def get_metrics(self):
        if (
            self.prediction_file is None
            or len(self.prediction_file) == 0
            or not os.path.exists(self.prediction_file)
        ):
            logger.error(f"Invalid prediction file: {self.prediction_file}")
            return []
        if (
            self.ground_truth_file is None
            or len(self.ground_truth_file) == 0
            or not os.path.exists(self.ground_truth_file)
        ):
            logger.error(f"Invalid ground truth file: {self.ground_truth_file}")
            return []

        metrics_list = [
            {"Data_Point": "NAN", "Precision": 0, "Recall": 0, "F1": 0, "Support": 0}
        ]
        
        missing_error_list, metrics_list = self.calculate_metrics()

        missing_error_df = pd.DataFrame(missing_error_list)
        missing_error_df.reset_index(drop=True, inplace=True)

        metrics_df = pd.DataFrame(metrics_list)
        metrics_df.reset_index(drop=True, inplace=True)

        with pd.ExcelWriter(self.output_file) as writer:
            missing_error_df.to_excel(writer, sheet_name="Missing_Error", index=False)
            metrics_df.to_excel(writer, sheet_name="Metrics", index=False)
        return missing_error_list, metrics_list, self.output_file

    def calculate_metrics(self):
        prediction_df = pd.read_excel(
            self.prediction_file, sheet_name=self.prediction_sheet_name
        )
        ground_truth_df = pd.read_excel(
            self.ground_truth_file, sheet_name=self.ground_truth_sheet_name
        )
        ground_truth_df = ground_truth_df[ground_truth_df["Checked"] == 1]

        tor_true = []
        tor_pred = []

        ter_true = []
        ter_pred = []

        ogc_true = []
        ogc_pred = []

        performance_fee_true = []
        performance_fee_pred = []

        missing_error_list = []
        data_point_list = ["tor", "ter", "ogc", "performance_fee"]

        if self.data_type == "page_filter":
            for index, row in ground_truth_df.iterrows():
                doc_id = row["doc_id"]
                # get first row with the same doc_id
                prediction_data = prediction_df[prediction_df["doc_id"] == doc_id].iloc[
                    0
                ]
                for data_point in data_point_list:
                    true_data, pred_data, missing_error_data = (
                        self.get_page_filter_true_pred_data(
                            doc_id, row, prediction_data, data_point
                        )
                    )
                    if data_point == "tor":
                        tor_true.extend(true_data)
                        tor_pred.extend(pred_data)
                    elif data_point == "ter":
                        ter_true.extend(true_data)
                        ter_pred.extend(pred_data)
                    elif data_point == "ogc":
                        ogc_true.extend(true_data)
                        ogc_pred.extend(pred_data)
                    elif data_point == "performance_fee":
                        performance_fee_true.extend(true_data)
                        performance_fee_pred.extend(pred_data)
                    missing_error_list.append(missing_error_data)
        else:
            prediction_doc_id_list = prediction_df["doc_id"].unique().tolist()
            ground_truth_doc_id_list = ground_truth_df["doc_id"].unique().tolist()
            # get intersection of doc_id_list
            doc_id_list = list(set(prediction_doc_id_list) & set(ground_truth_doc_id_list))
            # order by doc_id
            doc_id_list.sort()

            for doc_id in doc_id_list:
                prediction_data = prediction_df[prediction_df["doc_id"] == doc_id]
                ground_truth_data = ground_truth_df[ground_truth_df["doc_id"] == doc_id]
                for data_point in data_point_list:
                    true_data, pred_data, missing_error_data = (
                        self.get_data_extraction_true_pred_data(
                            doc_id, ground_truth_data, prediction_data, data_point
                        )
                    )
                    if data_point == "tor":
                        tor_true.extend(true_data)
                        tor_pred.extend(pred_data)
                    elif data_point == "ter":
                        ter_true.extend(true_data)
                        ter_pred.extend(pred_data)
                    elif data_point == "ogc":
                        ogc_true.extend(true_data)
                        ogc_pred.extend(pred_data)
                    elif data_point == "performance_fee":
                        performance_fee_true.extend(true_data)
                        performance_fee_pred.extend(pred_data)
                    missing_error_list.extend(missing_error_data)

        metrics_list = []
        for data_point in data_point_list:
            if data_point == "tor":
                precision, recall, f1 = self.get_specific_metrics(tor_true, tor_pred)
                tor_support = self.get_support_number(tor_true)
                metrics_list.append(
                    {
                        "Data_Point": data_point,
                        "Precision": precision,
                        "Recall": recall,
                        "F1": f1,
                        "Support": tor_support,
                    }
                )
                logger.info(
                    f"TOR Precision: {precision}, Recall: {recall}, F1: {f1}, Support: {tor_support}"
                )
            elif data_point == "ter":
                precision, recall, f1 = self.get_specific_metrics(ter_true, ter_pred)
                ter_support = self.get_support_number(ter_true)
                metrics_list.append(
                    {
                        "Data_Point": data_point,
                        "Precision": precision,
                        "Recall": recall,
                        "F1": f1,
                        "Support": ter_support,
                    }
                )
                logger.info(
                    f"TER Precision: {precision}, Recall: {recall}, F1: {f1}, Support: {ter_support}"
                )
            elif data_point == "ogc":
                precision, recall, f1 = self.get_specific_metrics(ogc_true, ogc_pred)
                ogc_support = self.get_support_number(ogc_true)
                metrics_list.append(
                    {
                        "Data_Point": data_point,
                        "Precision": precision,
                        "Recall": recall,
                        "F1": f1,
                        "Support": ogc_support,
                    }
                )
                logger.info(
                    f"OGC Precision: {precision}, Recall: {recall}, F1: {f1}, Support: {ogc_support}"
                )
            elif data_point == "performance_fee":
                precision, recall, f1 = self.get_specific_metrics(
                    performance_fee_true, performance_fee_pred
                )
                performance_fee_support = self.get_support_number(performance_fee_true)
                metrics_list.append(
                    {
                        "Data_Point": data_point,
                        "Precision": precision,
                        "Recall": recall,
                        "F1": f1,
                        "Support": performance_fee_support,
                    }
                )
                logger.info(
                    f"Performance Fee Precision: {precision}, Recall: {recall}, F1: {f1}, Support: {performance_fee_support}"
                )

        # get average metrics
        precision_list = [metric["Precision"] for metric in metrics_list]
        recall_list = [metric["Recall"] for metric in metrics_list]
        f1_list = [metric["F1"] for metric in metrics_list]
        metrics_list.append(
            {
                "Data_Point": "Average",
                "Precision": sum(precision_list) / len(precision_list),
                "Recall": sum(recall_list) / len(recall_list),
                "F1": sum(f1_list) / len(f1_list),
                "Support": sum([metric["Support"] for metric in metrics_list]),
            }
        )
        return missing_error_list, metrics_list

    def get_support_number(self, true_data: list):
        # get the count which true_data is 1
        return sum(true_data)

    def get_page_filter_true_pred_data(
        self,
        doc_id,
        ground_truth_data: pd.Series,
        prediction_data: pd.Series,
        data_point: str,
    ):
        ground_truth_list = ground_truth_data[data_point]
        if isinstance(ground_truth_list, str):
            ground_truth_list = json.loads(ground_truth_list)
        prediction_list = prediction_data[data_point]
        if isinstance(prediction_list, str):
            prediction_list = json.loads(prediction_list)

        true_data = []
        pred_data = []

        missing_error_data = {
            "doc_id": doc_id,
            "data_point": data_point,
            "missing": [],
            "error": [],
        }

        missing_data = []
        error_data = []

        if len(ground_truth_list) == 0 and len(prediction_list) == 0:
            true_data.append(1)
            pred_data.append(1)
            return true_data, pred_data, missing_error_data

        for prediction in prediction_list:
            if prediction in ground_truth_list:
                true_data.append(1)
                pred_data.append(1)
            else:
                true_data.append(0)
                pred_data.append(1)
                error_data.append(prediction)

        for ground_truth in ground_truth_list:
            if ground_truth not in prediction_list:
                true_data.append(1)
                pred_data.append(0)
                missing_data.append(ground_truth)
        missing_error_data = {
            "doc_id": doc_id,
            "data_point": data_point,
            "missing": missing_data,
            "error": error_data,
        }

        return true_data, pred_data, missing_error_data

    def get_data_extraction_true_pred_data(
        self,
        doc_id,
        ground_truth_data: pd.DataFrame,
        prediction_data: pd.DataFrame,
        data_point: str,
    ):
        dp_ground_truth = ground_truth_data[
            ground_truth_data["datapoint"] == data_point
        ]
        dp_prediction = prediction_data[prediction_data["datapoint"] == data_point]

        # add new column to store unique words for dp_ground_truth
        dp_ground_truth["unique_words"] = dp_ground_truth["raw_name"].apply(
            get_unique_words_text
        )
        ground_truth_unique_words = dp_ground_truth["unique_words"].unique().tolist()
        ground_truth_raw_names = dp_ground_truth["raw_name"].unique().tolist()
        # add new column to store unique words for dp_prediction
        dp_prediction["unique_words"] = dp_prediction["raw_name"].apply(
            get_unique_words_text
        )
        pred_unique_words = dp_prediction["unique_words"].unique().tolist()
        pred_raw_names = dp_prediction["raw_name"].unique().tolist()

        true_data = []
        pred_data = []

        missing_error_data = []

        if len(dp_ground_truth) == 0 and len(dp_prediction) == 0:
            true_data.append(1)
            pred_data.append(1)
            return true_data, pred_data, missing_error_data

        for index, prediction in dp_prediction.iterrows():
            pred_page_index = prediction["page_index"]
            pred_raw_name = prediction["raw_name"]
            pred_unique_words = prediction["unique_words"]
            pred_data_point_value = prediction["value"]
            pred_investment_type = prediction["investment_type"]

            find_raw_name_in_gt = [gt_raw_name for gt_raw_name in ground_truth_raw_names 
                                   if gt_raw_name in pred_raw_name or pred_raw_name in gt_raw_name]
            if pred_unique_words in ground_truth_unique_words or len(find_raw_name_in_gt) > 0:
                # get the ground truth data with the same unique words
                if pred_unique_words in ground_truth_unique_words:
                    gt_data = dp_ground_truth[
                        dp_ground_truth["unique_words"] == pred_unique_words
                    ].iloc[0]
                else:
                    gt_data = dp_ground_truth[
                        dp_ground_truth["raw_name"] == find_raw_name_in_gt[0]
                    ].iloc[0]
                gt_data_point_value = gt_data["value"]
                if pred_data_point_value == gt_data_point_value:
                    true_data.append(1)
                    pred_data.append(1)
                else:
                    true_data.append(0)
                    pred_data.append(1)
                    error_data = {
                        "doc_id": doc_id,
                        "data_point": data_point,
                        "page_index": pred_page_index,
                        "pred_raw_name": pred_raw_name,
                        "investment_type": pred_investment_type,
                        "error_type": "data value incorrect",
                        "error_value": pred_data_point_value,
                        "correct_value": gt_data_point_value,
                    }
                    missing_error_data.append(error_data)
            else:
                true_data.append(0)
                pred_data.append(1)
                error_data = {
                    "doc_id": doc_id,
                    "data_point": data_point,
                    "page_index": pred_page_index,
                    "pred_raw_name": pred_raw_name,
                    "investment_type": pred_investment_type,
                    "error_type": "raw name incorrect",
                    "error_value": pred_raw_name,
                    "correct_value": "",
                }
                missing_error_data.append(error_data)

        for index, ground_truth in dp_ground_truth.iterrows():
            gt_page_index = ground_truth["page_index"]
            gt_raw_name = ground_truth["raw_name"]
            gt_unique_words = ground_truth["unique_words"]
            gt_data_point_value = ground_truth["value"]
            gt_investment_type = ground_truth["investment_type"]
            
            find_raw_name_in_pred = [pred_raw_name for pred_raw_name in pred_raw_names 
                                   if gt_raw_name in pred_raw_name or pred_raw_name in gt_raw_name]
            
            if gt_unique_words not in pred_unique_words and \
                len(find_raw_name_in_pred) == 0:
                true_data.append(1)
                pred_data.append(0)
                error_data = {
                        "doc_id": doc_id,
                        "data_point": data_point,
                        "page_index": gt_page_index,
                        "pred_raw_name": "",
                        "investment_type": gt_investment_type,
                        "error_type": "raw name missing",
                        "error_value": pred_data_point_value,
                        "correct_value": gt_raw_name,
                    }
                missing_error_data.append(error_data)

        return true_data, pred_data, missing_error_data

    def get_specific_metrics(self, true_data: list, pred_data: list):
        precision = precision_score(true_data, pred_data)
        recall = recall_score(true_data, pred_data)
        f1 = f1_score(true_data, pred_data)
        return precision, recall, f1

    def get_datapoint_metrics(self):
        pass