training/pros_multiple_time_windows.py

"""
Derive features from PRO responses for multiple time windows and select time window
that gives the best signal.
"""

import numpy as np
import pandas as pd
import model_h
import matplotlib.pyplot as plt
from collections import defaultdict


def create_cols_for_plotting(pro_name, question_col_names=None, var_engagement=False):
    """
    Create a mapping for the PRO questions specified that allows plotting of the results
    from the same question with different time windows on the same grid. The key of the
    dictionary is the PRO question (e.g. 'EQ5DQ1') and the values are a list containing
    column names to be plotted (e.g. ['LatestEQ5DQ1', 'DiffLatestAvgEQ5DQ1TW1']).

    Args:
        pro_name (str): name of PRO.
        question_col_names (list, optional): a list of question names required for
                            plotting. Defaults to None.
        var_engagement (bool, optional): whether the variable to be plot is engagement.
                        Defaults to False.

    Returns:
        dict of (str:list): dictionary containing mapping where each key maps to a list
                 of column names.
    """
    cols_for_plotting = defaultdict(list)

    if var_engagement is False:
        for question in question_col_names:
            for time_window_num in range(1, 7):
                col_name = (
                    "DiffLatestAvg" + pro_name + question + "TW" + str(time_window_num)
                )
                cols_for_plotting[pro_name + question].append(col_name)
                if (pro_name == "SymptomDiary") & (question == "Q3"):
                    col_name = (
                        "ScaledSum" + pro_name + question + "TW" + str(time_window_num)
                    )
                    cols_for_plotting["ScaledSum" + pro_name + question].append(
                        col_name
                    )
            cols_for_plotting[pro_name + question].append(
                "DiffLatestPrev" + pro_name + question
            )
            if (pro_name == "EQ5D") | (pro_name == "MRC"):
                cols_for_plotting[pro_name + question].append(
                    "Latest" + pro_name + question
                )
            if (pro_name == "CAT") | (pro_name == "SymptomDiary"):
                cols_for_plotting[pro_name + question].append(
                    "WeekAvg" + pro_name + question
                )

    if var_engagement is True:
        for time_window_num in range(1, 7):
            col_name = "Engagement" + pro_name + "TW" + str(time_window_num)
            cols_for_plotting[pro_name].append(col_name)
    return cols_for_plotting


def plot_feature_signal(
    data, nrows, ncols, figsize, cols_to_plot, fig_name, outcome="ExacWithin3Months"
):
    """
    Plot boxplots for each multiple columns onto the same grid if multiple columns are
    specified.

    Args:
        data (pd.DataFrame): dataframe containing all data to plot and outcome column.
        nrows (int): number of rows for the subplot grid.
        ncols (int): number of columns for the subplot grid.
        figsize (tuple): (width, height) in inches.
        cols_to_plot (list): column names to plot.
        fig_name (str): name of figure required to save figure.
        outcome (str, optional): name of column to group values by for plotting the
                 data. Defaults to 'ExacWithinMonths'.

    Returns:
        None.
    """
    fig, ax = plt.subplots(nrows, ncols, figsize=figsize)
    if (nrows > 1) | (ncols > 1):
        ax = ax.flatten()
        for i, col in enumerate(cols_to_plot):
            data.boxplot(
                col,
                outcome,
                ax=ax[i],
                flierprops={"markersize": 2},
                medianprops={"color": "black"},
                # oxprops={"color": "black"},
            )
    else:
        for i, col in enumerate(cols_to_plot):
            data.boxplot(
                col,
                outcome,
                flierprops={"markersize": 2},
                medianprops={"color": "black"},
            )
    plt.tight_layout()
    plt.savefig("./plots/boxplots/" + fig_name + ".png")
    plt.close()


data = pd.read_pickle("./data/patient_labels_hosp_comm.pkl")
patient_details = pd.read_pickle("./data/patient_details.pkl")

data = data.merge(
    patient_details[["StudyId", "FirstSubmissionDate", "LatestPredictionDate"]],
    on="StudyId",
    how="left",
)

# Calculate the lookback start date. Will need this to aggreggate data for model
# features
data["LookbackStartDate"] = data["IndexDate"] - pd.DateOffset(days=180)

############################################################################
# Derive features from PRO responses
############################################################################
############################################
# Monthly PROs - EQ5D
############################################
pro_eq5d = pd.read_csv("<YOUR_DATA_PATH>/copd-dataset/CopdDatasetProEQ5D.txt", delimiter="|")
pro_eq5d = pro_eq5d.merge(
    data[["StudyId", "IndexDate", "FirstSubmissionDate", "LatestPredictionDate"]],
    on="StudyId",
    how="inner",
)

# EQ5DQ6 is a much less structured question compared to the other questions in EQ5D. A
# new score will be calculated using only EQ5DQ1-Q5 to prevent Q6 affecting the score.
pro_eq5d["EQ5DScoreWithoutQ6"] = pro_eq5d.loc[:, "EQ5DQ1":"EQ5DQ5"].sum(axis=1)

# Calculate engagement over service
pro_eq5d = model_h.calc_total_pro_engagement(pro_eq5d, "EQ5D")

# Calculate engagement over multiple time windows
for time_window in range(1, 7):
    pro_eq5d_engagement = model_h.calc_pro_engagement_in_time_window(
        pro_eq5d, "EQ5D", time_window=time_window, data=data
    )
    pro_eq5d = pro_eq5d.merge(
        pro_eq5d_engagement, on=["StudyId", "IndexDate"], how="left"
    )

# Calculate last PRO score
pro_eq5d = model_h.calc_last_pro_score(pro_eq5d, "EQ5D")

# Calculate the PRO score prior to the last PRO score
pro_eq5d = model_h.calc_pro_score_prior_to_latest(pro_eq5d, "EQ5D")

#############################
# Scores across time windows
#############################
# Mapping to calculate the difference between the latest PRO scores and both the average
# and previous PRO score
question_names_eq5d = ["Q1", "Q2", "Q3", "Q4", "Q5", "Q6", "Score", "ScoreWithoutQ6"]
mapping_eq5d = model_h.define_mapping_for_calcs(
    "EQ5D", question_names_eq5d, prefixes=["Avg", "Prev"]
)

# Calculate average PRO score across various time windows (months) prior to IndexDate,
# ignoring the latest PRO score
for time_window in range(1, 7):
    pro_eq5d = model_h.calc_pro_average(pro_eq5d, "EQ5D", time_window=time_window)
    for key in mapping_eq5d:
        model_h.calc_diff_pro_scores(
            pro_eq5d, "EQ5D", key, mapping_eq5d[key][0], time_window=time_window
        )

# Calculate difference between latest PRO score and PRO score prior to the latest
for key in mapping_eq5d:
    model_h.calc_diff_pro_scores(pro_eq5d, "EQ5D", key, mapping_eq5d[key][1])

# Remove unwanted columns and duplicates
pro_eq5d = pro_eq5d.loc[
    :,
    ~(
        pro_eq5d.columns.str.startswith("Avg")
        | pro_eq5d.columns.str.startswith("EQ5D")
        | pro_eq5d.columns.str.startswith("Prev")
        | pro_eq5d.columns.str.startswith("Response")
    ),
]
pro_eq5d = pro_eq5d.drop(
    columns=[
        "Score",
        "SubmissionTime",
        "FirstSubmissionDate",
        "TimeInService",
        "TimeSinceSubmission",
        "LatestPredictionDate",
        "LatestPRODate",
    ]
)
pro_eq5d = pro_eq5d.drop_duplicates()

############################################
# Weekly PROs - MRC
############################################
pro_mrc = pd.read_csv("<YOUR_DATA_PATH>/copd-dataset/CopdDatasetProMrc.txt", delimiter="|")
pro_mrc = pro_mrc.merge(
    data[["StudyId", "IndexDate", "FirstSubmissionDate", "LatestPredictionDate"]],
    on="StudyId",
    how="inner",
)

# Calculate engagement over service
pro_mrc = model_h.calc_total_pro_engagement(pro_mrc, "MRC")

# Calculate engagement over multiple time windows
for time_window in range(1, 7):
    pro_mrc_engagement = model_h.calc_pro_engagement_in_time_window(
        pro_mrc, "MRC", time_window=time_window, data=data
    )
    pro_mrc = pro_mrc.merge(pro_mrc_engagement, on=["StudyId", "IndexDate"], how="left")

# Calculate last PRO score
pro_mrc = model_h.calc_last_pro_score(pro_mrc, "MRC")

# Calculate the PRO score prior to the last PRO score
pro_mrc = model_h.calc_pro_score_prior_to_latest(pro_mrc, "MRC")

#############################
# Scores across time windows
#############################
# Mapping to calculate the difference between the latest PRO scores and both the average
# and previous PRO score
question_names_mrc = ["Q1"]
mapping_mrc = model_h.define_mapping_for_calcs(
    "MRC", question_names_mrc, prefixes=["Avg", "Prev"]
)

# Calculate average PRO score across various time windows (months) prior to IndexDate,
# ignoring the latest PRO score
for time_window in range(1, 7):
    pro_mrc = model_h.calc_pro_average(pro_mrc, "MRC", time_window=time_window)
    for key in mapping_mrc:
        model_h.calc_diff_pro_scores(
            pro_mrc, "MRC", key, mapping_mrc[key][0], time_window=time_window
        )

# Calculate difference between latest PRO score and PRO score prior to the latest
for key in mapping_mrc:
    model_h.calc_diff_pro_scores(pro_mrc, "MRC", key, mapping_mrc[key][1])

# Remove unwanted columns and duplicates
pro_mrc = pro_mrc.loc[
    :,
    ~(
        pro_mrc.columns.str.startswith("Avg")
        | pro_mrc.columns.str.startswith("MRC")
        | pro_mrc.columns.str.startswith("Prev")
        | pro_mrc.columns.str.startswith("Response")
    ),
]
pro_mrc = pro_mrc.drop(
    columns=[
        "SubmissionTime",
        "Score",
        "FirstSubmissionDate",
        "TimeInService",
        "TimeSinceSubmission",
        "LatestPredictionDate",
        "LatestPRODate",
    ]
)
pro_mrc = pro_mrc.drop_duplicates()

############################################
# Daily PROs - CAT
############################################
pro_cat = pd.read_csv("<YOUR_DATA_PATH>/copd-dataset/CopdDatasetProCat.txt", delimiter="|")
pro_cat = pro_cat.merge(
    data[["StudyId", "IndexDate", "FirstSubmissionDate", "LatestPredictionDate"]],
    on="StudyId",
    how="inner",
)

# Calculate engagement over service and 1 month prior to index date
pro_cat = model_h.calc_total_pro_engagement(pro_cat, "CAT")

# Calculate engagement over multiple time windows
for time_window in range(1, 7):
    pro_cat_engagement = model_h.calc_pro_engagement_in_time_window(
        pro_cat, "CAT", time_window=time_window, data=data
    )
    pro_cat = pro_cat.merge(pro_cat_engagement, on=["StudyId", "IndexDate"], how="left")

# Calculate PRO average for the week before the index date
pro_cat = model_h.calc_pro_average(pro_cat, "CAT", avg_period="WeeklyAvg")

# Calculate PRO average for the week before most recent week to the index date
pro_cat = model_h.calc_pro_average(pro_cat, "CAT", avg_period="WeekPrevAvg")

#############################
# Scores across time windows
#############################
# Mapping to calculate the difference between the latest PRO scores and both the average
# and previous PRO score
question_names_cat = ["Q1", "Q2", "Q3", "Q4", "Q5", "Q6", "Q7", "Q8", "Score"]
mapping_cat = model_h.define_mapping_for_calcs(
    "CAT", question_names_cat, prefixes=["LongerAvg", "WeekPrevAvg"]
)

# Calculate average PRO score across various time windows (months) prior to IndexDate,
# ignoring the latest PRO score
for time_window in range(1, 7):
    pro_cat = model_h.calc_pro_average(
        pro_cat, "CAT", time_window=time_window, avg_period="LongerAvg"
    )
    for key in mapping_cat:
        model_h.calc_diff_pro_scores(
            pro_cat, "CAT", key, mapping_cat[key][0], time_window=time_window
        )

# Calculate difference between latest PRO score and PRO score prior to the latest
for key in mapping_cat:
    model_h.calc_diff_pro_scores(pro_cat, "CAT", key, mapping_cat[key][1])

# Remove unwanted columns and duplicates
pro_cat = pro_cat.loc[
    :,
    ~(
        pro_cat.columns.str.startswith("WeekPrev")
        | pro_cat.columns.str.startswith("Longer")
        | pro_cat.columns.str.startswith("CAT")
        | pro_cat.columns.str.startswith("Response")
    ),
]
pro_cat = pro_cat.drop(
    columns=[
        "Score",
        "SubmissionTime",
        "FirstSubmissionDate",
        "LatestPredictionDate",
        "TimeInService",
        "AvgStartDate",
        "WeekStartDate",
    ]
)
pro_cat = pro_cat.drop_duplicates()

############################################
# Daily PROs - Symptom Diary
############################################
# Symptom diary have some questions that are numeric and some that are categorical
pro_sd = pd.read_csv(
    "<YOUR_DATA_PATH>/copd-dataset/CopdDatasetProSymptomDiary.txt", delimiter="|"
)
pro_sd = pro_sd.merge(
    data[["StudyId", "IndexDate", "FirstSubmissionDate", "LatestPredictionDate"]],
    on="StudyId",
    how="inner",
)

# Calculate engagement over service
pro_sd = model_h.calc_total_pro_engagement(pro_sd, "SymptomDiary")
pro_sd_engagement = pro_sd[
    ["StudyId", "PatientId", "IndexDate", "TotalEngagementSymptomDiary"]
]

# Calculate engagement over multiple time windows
for time_window in range(1, 7):
    pro_sd_engagement_tw = model_h.calc_pro_engagement_in_time_window(
        pro_sd, "SymptomDiary", time_window=time_window, data=data
    )
    pro_sd_engagement = pro_sd_engagement.merge(
        pro_sd_engagement_tw, on=["StudyId", "IndexDate"], how="left"
    )
pro_sd_engagement = pro_sd_engagement.drop_duplicates()

###############################
# Numeric questions
# (Q1, Q2)
# Q3 included for comparison
###############################
# Calculate PRO average for the week before the index date
pro_sd_numeric = pro_sd[
    [
        "StudyId",
        "PatientId",
        "IndexDate",
        "SubmissionTime",
        "Score",
        "SymptomDiaryQ1",
        "SymptomDiaryQ2",
        "SymptomDiaryQ3",
    ]
]
pro_sd_numeric = model_h.calc_pro_average(
    pro_sd_numeric, "SymptomDiary", avg_period="WeeklyAvg"
)

# Calculate PRO average for the week before most recent week to the index date
pro_sd_numeric = model_h.calc_pro_average(
    pro_sd_numeric, "SymptomDiary", avg_period="WeekPrevAvg"
)

#############################
# Scores across time windows
#############################
# Mapping to calculate the difference between the latest PRO scores and both the average
# and previous PRO score
question_names_sd = ["Q1", "Q2", "Q3"]
mapping_sd = model_h.define_mapping_for_calcs(
    "SymptomDiary", question_names_sd, prefixes=["LongerAvg", "WeekPrevAvg"]
)

# Calculate average PRO score across various time windows (months) prior to IndexDate,
# ignoring the latest PRO score
for time_window in range(1, 7):
    pro_sd_numeric = model_h.calc_pro_average(
        pro_sd_numeric, "SymptomDiary", time_window=time_window, avg_period="LongerAvg"
    )
    for key in mapping_sd:
        model_h.calc_diff_pro_scores(
            pro_sd_numeric,
            "SymptomDiary",
            key,
            mapping_sd[key][0],
            time_window=time_window,
        )

# Calculate difference between latest PRO score and PRO score prior to the latest week
for key in mapping_sd:
    model_h.calc_diff_pro_scores(pro_sd_numeric, "SymptomDiary", key, mapping_sd[key][1])

###############################
# Binary questions
# (Q3)
###############################
# Calculate sum of binary values across previous months
sd_sum_all = pro_sd_numeric[["StudyId", "IndexDate"]]
sd_sum_all = sd_sum_all.drop_duplicates()
for time_window in range(1, 7):
    sd_sum = model_h.calc_sum_binary_vals(
        pro_sd_numeric, binary_cols=["SymptomDiaryQ3"], time_window=time_window
    )
    sd_sum_all = sd_sum_all.merge(sd_sum, on=["StudyId", "IndexDate"], how="left")

# Scale sums by how often patients responded
sd_sum_all = sd_sum_all.merge(
    pro_sd_engagement, on=["StudyId", "IndexDate"], how="left"
)
mapping_scaling = {}
for time_window in range(1, 7):
    mapping_scaling["SumSymptomDiaryQ3TW" + str(time_window)] = (
        "EngagementSymptomDiaryTW" + str(time_window)
    )
for key in mapping_scaling:
    model_h.scale_sum_to_response_rate(sd_sum_all, key, mapping_scaling[key])

# Combine numeric and binary dfs
pro_sd_full = pro_sd_numeric.merge(
    sd_sum_all, on=["StudyId", "PatientId", "IndexDate"], how="left"
)

# Remove unwanted columns from numeric df
pro_sd_full = pro_sd_full.loc[
    :,
    ~(
        pro_sd_full.columns.str.startswith("WeekPrev")
        | pro_sd_full.columns.str.startswith("Longer")
        | pro_sd_full.columns.str.startswith("Symptom")
        | pro_sd_full.columns.str.startswith("Sum")
        | pro_sd_full.columns.str.startswith("Response")
    ),
]
pro_sd_full = pro_sd_full.drop(
    columns=[
        "Score",
        "SubmissionTime",
        "AvgStartDate",
        "TimeWindowStartDate",
        "WeekStartDate",
    ]
)
pro_sd_full = pro_sd_full.drop_duplicates()

############################################################################
# Combine PROs with main df
############################################################################
data = data.merge(pro_eq5d, on=["StudyId", "PatientId", "IndexDate"], how="left")
data = data.merge(pro_mrc, on=["StudyId", "PatientId", "IndexDate"], how="left")
data = data.merge(pro_cat, on=["StudyId", "PatientId", "IndexDate"], how="left")
data = data.merge(pro_sd_full, on=["StudyId", "PatientId", "IndexDate"], how="left")

# Calculate mean for features grouped by outcome
feat_to_explore = data.loc[:, "TotalEngagementEQ5D":"ScaledSumSymptomDiaryQ3TW6"]
feat_to_explore.loc[:, "ExacWithin3Months"] = data.loc[:, "ExacWithin3Months"]
grouped_data_by_outcome = feat_to_explore.groupby("ExacWithin3Months").mean()
grouped_data_by_outcome = grouped_data_by_outcome.T

############################################################################
# Plotting
############################################################################
##############################
# EQ5D Boxplots
##############################
# Plotting score values
cols_for_plotting = model_h.create_cols_for_plotting(
    "EQ5D", question_col_names=question_names_eq5d
)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=3,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_boxplot",
    )

# Plotting engagement
cols_for_plotting = model_h.create_cols_for_plotting("EQ5D", var_engagement=True)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=2,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_engagement",
    )

##############################
# MRC Boxplots
##############################
# Plotting score values
cols_for_plotting = model_h.create_cols_for_plotting(
    "MRC", question_col_names=question_names_mrc
)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=3,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_boxplot",
    )

# Plotting engagement
cols_for_plotting = model_h.create_cols_for_plotting("MRC", var_engagement=True)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=2,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_engagement",
    )

##############################
# CAT Boxplots
##############################
# Plotting score values
cols_for_plotting = model_h.create_cols_for_plotting(
    "CAT", question_col_names=question_names_cat
)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=3,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_boxplot",
    )
# Plotting engagement
cols_for_plotting = model_h.create_cols_for_plotting("CAT", var_engagement=True)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=2,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_engagement",
    )

##############################
# SymptomDiary Boxplots
##############################
# Plotting score values
cols_for_plotting = model_h.create_cols_for_plotting(
    "SymptomDiary", question_col_names=question_names_sd
)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=3,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_boxplot",
    )

# Plotting engagement
cols_for_plotting = model_h.create_cols_for_plotting("SymptomDiary", var_engagement=True)
for key in cols_for_plotting:
    model_h.plot_feature_signal(
        data,
        nrows=2,
        ncols=3,
        figsize=(12, 12),
        cols_to_plot=cols_for_plotting[key],
        fig_name=key + "_engagement",
    )