import numpy as np
import pandas as pd

from languages import en, ru


category_init = "label"
certainty_init = "score"


def filter_results(results: pd.DataFrame, top_k=0.95):
    certs = results[certainty_init].to_numpy()
    cum_certs = certs.cumsum()
    do_no_show = cum_certs < top_k
    first_not_to_show_id = np.argmin(do_no_show) + 1
    results = results.iloc[:first_not_to_show_id]
    results = results[results[certainty_init] >= 0.01]
    return results


def process_keys(results: pd.DataFrame, lang):
    category = {en: "Category", ru: "Категория"}
    certainty = {en: "Certainty", ru: "Уверенность"}
    results = results.rename(
        columns={
            category_init: category.get(lang, category[en]),
            certainty_init: certainty.get(lang, certainty[en]),
        }
    )
    return results


def process_categories(results, lang):
    categories = {
        en: {
            "math": "Math",
            "astro-ph": "Astrophysics",
            "cond-mat": "Condensed matter physics",
            "hep-ph": "High energy physics -- Phenomenology",
            "physics": "Physics",
            "hep-th": "High energy physics -- Theory",
            "cs": "Computer Science",
            "quant-ph": "Quantum physics",
            "gr-qc": "General Relativity and Quantum Cosmology",
            "math-ph": "Mathematical Physics",
            "nucl-th": "Nuclear Theory",
            "eess": "Electrical Engineering and Systems Science",
            "q-bio": "Quantitative Biology",
            "nlin": "Nonlinear Sciences",
            "stat": "Statistics",
            "hep-lat": "High Energy Physics - Lattice",
            "hep-ex": "High Energy Physics - Experiment",
            "nucl-ex": "Nuclear Experiment",
            "econ": "Economins",
            "q-alg": "Quantum Algebra",
            "q-fin": "Quantitative Finance",
            "alg-geom": "Algebraic Geometry",
            "supr-con": "Superconductivity",
            "chao-dyn": "Chaotic dynamics",
            "dg-ga": "Differential Geometry",
            "funct-an": "Functional analysis",
            "atom-ph": "Atomic physics",
            "chem-ph": "Chemical Physics",
            "ao-sci": "Atmospheric and Oceanic Physics",
            "acc-phys": "Accelerator Physics",
            "bayes-an": "Bayesian statistics",
            "plasm-ph": "Plasma Physics",
        },
        ru: {
            "math": "Математика",
            "astro-ph": "Астрофизика",
            "cond-mat": "Физика конденсированного состояния",
            "hep-ph": "Физика элементарных частиц -- Феноменология",
            "physics": "Физика",
            "hep-th": "Физика элементарных частиц -- Теория",
            "cs": "Компьютерные науки",
            "quant-ph": "Квантовая физика",
            "gr-qc": "Общая теория относительности и квантовая космология",
            "math-ph": "Математическая физика",
            "nucl-th": "Ядерная физика",
            "eess": "Электротехника и системоведение",
            "q-bio": "Количественная биология",
            "nlin": "Нелинейные науки",
            "stat": "Статистика",
            "hep-lat": "Физика элементарных частиц -- Решетки",
            "hep-ex": "Экспериментальная физика элементарных частиц",
            "nucl-ex": "Ядерный эксперимент",
            "econ": "Экономика",
            "q-alg": "Квантовая алгебра",
            "q-fin": "Количественные финансы",
            "alg-geom": "Алгебраическая геометрия",
            "supr-con": "Сверхпроводимость",
            "chao-dyn": "Теория хаоса",
            "dg-ga": "Дифференциальная геометрия",
            "funct-an": "Функциональный анализ",
            "atom-ph": "Атомная физика",
            "chem-ph": "Химическая физика",
            "ao-sci": "Физика атмосферы и океана",
            "acc-phys": "Физика ускорителей",
            "bayes-an": "Байесовская статистика",
            "plasm-ph": "Физика плазмы",
        },
    }

    def process_category(category):
        if "." in category:
            category = category[: category.index(".")]
        return categories.get(lang, {}).get(category, category)

    results[category_init] = results[category_init].apply(process_category)
    return results


def process_certainities(results):
    results[certainty_init] = results[certainty_init].apply(
        lambda certainty: "{0:0.2f}%".format(100 * certainty)
    )
    return results


def process_results(results, lang):
    results = pd.DataFrame(results)
    results = process_categories(results, lang)
    results = results.groupby(by=category_init, as_index=False).sum()
    results = results.sort_values(by=[certainty_init], ascending=False)
    results = filter_results(results)
    results = process_certainities(results)
    results = process_keys(results, lang)
    return results