File size: 15,566 Bytes
e69d4e4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 | """Prepare final train set for cross-validation (K fold encoded, scaled and imputed)."""
import copd
# import matplotlib.pyplot as plt
from lenusml import crossvalidation
import os
import pandas as pd
import numpy as np
import seaborn as sns
from sklearn.preprocessing import MinMaxScaler
from sklearn.impute import SimpleImputer
sns.set(style='darkgrid', context='talk')
sns.set_palette('dark')
muted = sns.palettes.color_palette(palette='muted')
dark = sns.palettes.color_palette(palette='dark')
data_dir = '<YOUR_DATA_PATH>/train_data/'
cohort_info_dir = '../data/cohort_info/'
output_data_dir = '../data/models/model1'
fold_patients = np.load(os.path.join(cohort_info_dir, 'fold_patients.npy'),
allow_pickle=True)
data = pd.read_pickle(os.path.join(data_dir, 'train_data.pkl'))
exacs = data[data.IsExac == 1]
exac_patients = exacs.StudyId.unique()
# non_exac_patients = np.setdiff1d(data.StudyId, exac_patients)
# len(non_exac_patients)
# exac_counts = exacs.groupby('StudyId')['IsExac'].count().reset_index()
# exac_counts = pd.concat([exac_counts,
# pd.DataFrame({'StudyId': non_exac_patients,
# 'IsExac': len(non_exac_patients)*[0]})])
#
# exac_counts = exac_counts.merge(data[['StudyId', 'Sex', 'SmokingStatus',
# 'RequiredAcuteNIV', 'RequiredICUAdmission']],
# on='StudyId', how='left')
###############################################
# Map the True/False cols to integers
###############################################
bool_mapping = {True: 1, False: 0}
data['RequiredAcuteNIV'] = data.RequiredAcuteNIV.replace(bool_mapping)
data['RequiredICUAdmission'] = data.RequiredICUAdmission.replace(bool_mapping)
# Map the M and F sex column to binary (1=F)
sex_mapping = {'F': 1, 'M': 0}
data['Sex_F'] = data.Sex.map(sex_mapping)
data = data.drop(columns=['Sex'])
##############################################################
# Read daily PRO responses, calculate aggregations and merge
##############################################################
cat = pd.read_csv(os.path.join('<YOUR_DATA_PATH>/copd-dataset/', 'CopdDatasetProCat.txt'),
delimiter="|")
symptom_diary = pd.read_csv(
os.path.join('<YOUR_DATA_PATH>/copd-dataset/', 'CopdDatasetProSymptomDiary.txt'),
usecols=['PatientId', 'SubmissionTime', 'SymptomDiaryQ1', 'SymptomDiaryQ2',
'SymptomDiaryQ3', 'SymptomDiaryQ8', 'SymptomDiaryQ9', 'SymptomDiaryQ10'],
delimiter="|")
cat['SubmissionTime'] = pd.to_datetime(cat.SubmissionTime,
utc=True).dt.normalize()
symptom_diary['SubmissionTime'] = pd.to_datetime(symptom_diary.SubmissionTime,
utc=True).dt.normalize()
# Filter for train patients
cat = cat[cat.PatientId.isin(data.PatientId)]
symptom_diary = symptom_diary[symptom_diary.PatientId.isin(data.PatientId)]
# Merge daily PROs accounting for days where patients answered the same PRO more than once
# per day
daily_pros = pd.merge(cat.drop_duplicates(subset=['PatientId', 'SubmissionTime']),
symptom_diary.drop_duplicates(subset=['PatientId',
'SubmissionTime']),
on=['PatientId', 'SubmissionTime'], how='inner')
# Calculate rolling mean on previous days for numeric PROs
numeric_pros = ['CATQ1', 'CATQ2', 'CATQ3', 'CATQ4', 'CATQ5', 'CATQ6', 'CATQ7',
'CATQ8', 'SymptomDiaryQ1', 'SymptomDiaryQ2', 'Score']
mean_pros = copd.rolling_mean_previous_period(df=daily_pros, cols=numeric_pros,
date_col='SubmissionTime',
id_col='StudyId', window=3)
# Merge the averaged PROs with the original responses and calculate differences
daily_pros = daily_pros.merge(mean_pros, on=['StudyId', 'SubmissionTime'], how='left')
daily_pros = copd.calculate_diff_from_rolling_mean(df=daily_pros, cols=numeric_pros)
# Remove the rolling average columns
daily_pros = daily_pros.loc[:, ~daily_pros.columns.str.endswith('_ave')]
# Merge PROs with full train data
train_data = pd.merge_asof(data.sort_values(by='DateOfEvent'), daily_pros.drop(
columns=['StudyId']).sort_values(by='SubmissionTime'),
left_on='DateOfEvent', right_on='SubmissionTime',
by='PatientId', direction='backward')
################################################
# Include comorbidities from Lenus service
################################################
comorbidities = pd.read_csv('<YOUR_DATA_PATH>/copd-dataset/CopdDatasetCoMorbidityDetails.txt',
delimiter='|')
comorbidities = comorbidities.drop(columns=['Id', 'Created'])
# Get list of comorbidities captured in the service
comorbidity_list = list(comorbidities.columns)
comorbidity_list.remove('PatientId')
# Filter for train patients
comorbidities = comorbidities[comorbidities.PatientId.isin(data.PatientId)]
print('Train patients with entries in CopdDatasetCoMorbidityDetails: {} out of {}'.format(
len(comorbidities), len(data.PatientId.unique())))
comorbidities[comorbidity_list] = comorbidities[comorbidity_list].replace(
bool_mapping).fillna(0)
print('Comorbidity counts:', '\n', comorbidities[comorbidity_list].sum())
# Merge with train data, infill nans and get counts
train_data = train_data.merge(comorbidities, on='PatientId', how='left')
print('Comorbidity counts after merging with patient days:', '\n',
train_data[comorbidity_list].sum())
train_data[comorbidity_list] = train_data[comorbidity_list].fillna(0)
# Get comorb counts for each patient
train_data['Comorbidities'] = train_data[comorbidity_list].sum(axis=1)
comorb_counts = train_data.groupby('StudyId')['Comorbidities'].max().reset_index()
# print('Patient comorbidity counts after infilling missing values: \n',
# comorb_counts.value_counts())
comorb_counts.loc[comorb_counts.StudyId.isin(exac_patients), 'IsExacPatient'] = 1
comorb_counts['IsExacPatient'] = comorb_counts['IsExacPatient'].fillna(0)
# Drop comorbidities columns from train data but retain AsthmaOverlap
comorbidity_list.remove('AsthmaOverlap')
train_data = train_data.drop(columns=comorbidity_list)
###############################################################
# Include inhaler type from Lenus service
###############################################################
# Load inhaler data
inhaler_type = pd.read_csv('<YOUR_DATA_PATH>/copd-dataset/CopdDatasetUsualTherapies.txt',
delimiter='|', usecols=['StudyId', 'InhalerType'])
# Filter for train patients
inhaler_type = inhaler_type[inhaler_type.StudyId.isin(data.StudyId)]
# Create new feature for triple therapy ('LABA-LAMA-ICS' or 'LAMA +LABA-ICS')
inhaler_type = copd.triple_inhaler_therapy_service(
df=inhaler_type, id_col='StudyId', inhaler_col='InhalerType', include_mitt=True)
print('Patients taking triple inhaler therapy: ', '\n',
inhaler_type.TripleTherapy.value_counts())
train_data = train_data.merge(inhaler_type, on='StudyId', how='left')
#####################################
# Map some categorical features
#####################################
# Replace SDQ8 with strings for phlegm difficulty and infill as None where no phlegm
# reported in CAT
train_data['SymptomDiaryQ8'] = train_data.SymptomDiaryQ8.replace(
{1: 'Not difficult', 2: 'A little difficult', 3: 'Quite difficult',
4: 'Very difficult', np.nan: 'None'})
# Replace SDQ9 with strings for phlegm consistency and infill as None where no phlegm
# reported in CAT
train_data['SymptomDiaryQ9'] = train_data.SymptomDiaryQ9.replace(
{1: 'Watery', 2: 'Sticky liquid', 3: 'Semi-solid', 4: 'Solid', np.nan: 'None'})
# Replace SDQ10 with strings for phlegm colour and infill as None where no phlegm
# reported in CAT
train_data['SymptomDiaryQ10'] = train_data.SymptomDiaryQ10.replace(
{1: 'White', 2: 'Yellow', 3: 'Green', 4: 'Dark green', np.nan: 'None'})
# Replace smoking status with strings
train_data['SmokingStatus'] = train_data.SmokingStatus.replace(
{1: 'Smoker', 2: 'Ex-smoker', 3: 'Non-smoker'})
train_data['InExacWindow'] = train_data.IsExac.replace({0: False, 1: True})
#####################################################
# Calculate DaysSinceCAT and filter data if required
#####################################################
train_data['DaysSinceCAT'] = (train_data.DateOfEvent -
train_data.SubmissionTime).dt.days.astype('int')
DaysSinceCAT_cutoff = 14
train_data = train_data[train_data.DaysSinceCAT <= DaysSinceCAT_cutoff]
#####################################
# Bin some numeric features
#####################################
# Bin days since last exacerbation
exac_bins = [-1, 0, 21, 90, 180, np.inf]
exac_labels = ['None', '<21 days', '21 - 89 days', '90 - 179 days', '>= 180 days']
train_data['DaysSinceLastExac'] = copd.bin_numeric_column(
col=train_data['DaysSinceLastExac'], bins=exac_bins, labels=exac_labels)
# Bin patient age
age_bins = [0, 50, 60, 70, 80, np.inf]
age_labels = ['<50', '50-59', '60-69', '70-79', '80+']
train_data['Age'] = copd.bin_numeric_column(
col=train_data['Age'], bins=age_bins, labels=age_labels)
# Bin number of comorbidities
comorb_bins = [0, 1, 3, np.inf]
comorb_labels = ['None', '1-2', '3+']
train_data['Comorbidities'] = copd.bin_numeric_column(
col=train_data['Comorbidities'], bins=comorb_bins, labels=comorb_labels)
comorb_counts['Comorbidities_binned'] = copd.bin_numeric_column(
col=comorb_counts['Comorbidities'], bins=comorb_bins, labels=comorb_labels)
# Bin patient spirometry at onboarding
spirometry_bins = [0, 30, 50, 80, np.inf]
spirometry_labels = ['Very severe', 'Severe', 'Moderate', 'Mild']
train_data['FEV1PercentPredicted'] = copd.bin_numeric_column(
col=train_data['LungFunction_FEV1PercentPredicted'], bins=spirometry_bins,
labels=spirometry_labels)
train_data = train_data.drop(columns=['LungFunction_FEV1PercentPredicted'])
# Assign patients without spirometry in service data to the Mild category
train_data.loc[
train_data['FEV1PercentPredicted'] == 'nan', 'FEV1PercentPredicted'] = 'Mild'
train_data['FEV1PercentPredicted'].value_counts()
##################################
# Service eosinophils feature
##################################
train_data['HighestEosinophilCount_0_3'] = np.where(
train_data['LabsHighestEosinophilCount'] >= 0.3, 1, 0)
train_data = train_data.drop(columns=['LabsHighestEosinophilCount'])
# import matplotlib.pyplot as plt
# def plot_categorical_against_target(*, df, column, target, savefig=False,
# output_dir=None, label_rotation=None,
# category_order=None):
# (df.groupby(target)[column].value_counts(normalize=True).mul(100).rename('Percent')
# .reset_index().pipe((sns.catplot, 'data'), x=column, y='Percent', hue=target,
# kind='bar', alpha=0.8, order=category_order))
# if label_rotation:
# plt.xticks(rotation=label_rotation, ha='right', rotation_mode='anchor')
# if savefig:
# plt.savefig(os.path.join(output_dir, column + '.png'), bbox_inches='tight',
# dpi=150)
# plot_categorical_against_target(df=train_data, column= 'SymptomDiaryQ10',
# target='InExacWindow', label_rotation=45,
# category_order=None, savefig=True,
# output_dir='../data/plots/')
# plt.show()
# plot_categorical_against_target(df=eosinophils, column= 'HighestEosinophilCount_0_3',
# target='IsExacPatient', label_rotation=None,
# category_order=None, savefig=True,
# output_dir='../data/plots/')
# plt.show()
# categorical_cols = ['Sex_F', 'RequiredAcuteNIV', 'RequiredICUAdmission',
# 'SmokingStatus', 'Comorbidities',
# 'CATQ1', 'CATQ2', 'CATQ3', 'CATQ4', 'CATQ5', 'CATQ6', 'CATQ7',
# 'CATQ8', 'SymptomDiaryQ1', 'SymptomDiaryQ2', 'SymptomDiaryQ3']
# for column in categorical_cols:
# plot_categorical_against_target(df=train_data, column=column, target='InExacWindow',
# savefig=True, output_dir='../data/plots/')
# def plot_numerical_against_target(*, df, column, target, bins=10, savefig=False,
# output_dir=None):
# sns.displot(x=column, hue=target, data=df, stat='density', bins=bins,
# common_norm=False)
# if savefig:
# plt.savefig(os.path.join(output_dir, column + '.png'), bbox_inches='tight',
# dpi=150)
# for col in numeric_pros:
# plot_numerical_against_target(
# df=train_data, column=col + '_diff', target='InExacWindow', bins=10,
# savefig=True, output_dir='../data/plots')
# plt.show()
# plot_numerical_against_target(
# df=spirometry, column='LungFunction_FEV1PercentPredicted',
# target='IsExacPatient', bins=20,
# savefig=True, output_dir='../data/plots')
# plt.show()
categorical_columns = ['SmokingStatus', 'SymptomDiaryQ8', 'SymptomDiaryQ9',
'SymptomDiaryQ10', 'DaysSinceLastExac', 'Age', 'Comorbidities',
'FEV1PercentPredicted']
train_data[categorical_columns] = train_data[categorical_columns].astype("str")
data_encoded = copd.kfold_encode_train_data(df=train_data, fold_patients=fold_patients,
cols_to_encode=categorical_columns,
target='IsExac', id_col='StudyId')
data_encoded = data_encoded.drop(columns=categorical_columns, axis=1)
###################################
# Scale data
###################################
data_encoded = data_encoded.drop(columns=['PatientId', 'InExacWindow',
'DateOfEvent', 'SubmissionTime',
'FirstSubmissionDate', 'LatestPredictionDate'])
scaler = MinMaxScaler()
train_data_scaled = crossvalidation.kfold_process_train_data(df=data_encoded,
fold_patients=fold_patients,
processor=scaler,
id_col='StudyId',
target='IsExac')
###################################
# Infill missing data with median
###################################
# K-fold impute data with the median
imputer = SimpleImputer(missing_values=np.nan, strategy='median')
train_data_imputed = crossvalidation.kfold_process_train_data(df=train_data_scaled,
fold_patients=fold_patients,
processor=imputer,
id_col='StudyId',
target='IsExac')
#########################################
# Save final data
#########################################
# Train data
os.makedirs(output_data_dir, exist_ok=True)
train_data_imputed.to_pickle(os.path.join(output_data_dir, 'train_data_cv.pkl'))
print('Final train data saved (CV)')
|