File size: 8,903 Bytes
000de75 | 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 | """Script that performs encoding of categorical features and imputation.
Performs encoding of categorical features, and imputation of missing values. After encoding
and imputation are performed, features are dropped. Two versions of the data is saved:
imputed and not imputed dataframes.
"""
import pandas as pd
import numpy as np
import os
import sys
import yaml
import json
import joblib
import encoding
import imputation
with open("./training/config.yaml", "r") as config:
config = yaml.safe_load(config)
# Specify which model to generate features for
model_type = config["model_settings"]["model_type"]
# Setup log file
log = open("./training/logging/encode_and_impute_" + model_type + ".log", "w")
sys.stdout = log
# Dataset to process - set through config file
data_to_process = config["model_settings"]["data_to_process"]
# Load data
data = pd.read_pickle(
os.path.join(
config["outputs"]["processed_data_dir"],
"{}_combined_{}.pkl".format(data_to_process, model_type),
)
)
############################################################################
# Target encode categorical data
############################################################################
categorical_cols = [
"LatestSymptomDiaryQ8",
"LatestSymptomDiaryQ9",
"LatestSymptomDiaryQ10",
"DaysSinceLastExac",
"AgeBinned",
"Comorbidities",
"FEV1PercentPredicted",
]
# Multiple types of nans present in data ('nan' and np.NaN). Convert all these to 'nan' for
# categorical columns
for categorical_col in categorical_cols:
data[categorical_col] = data[categorical_col].replace(np.nan, "nan")
if data_to_process == "train":
# Get target encodings for entire train set
target_encodings = encoding.get_target_encodings(
train_data=data,
cols_to_encode=categorical_cols,
target_col="ExacWithin3Months",
smooth="auto",
)
train_encoded = encoding.apply_target_encodings(
data=data,
cols_to_encode=categorical_cols,
encodings=target_encodings,
drop_categorical_cols=False,
)
json.dump(
target_encodings,
open("./data/artifacts/target_encodings_" + model_type + ".json", "w"),
)
# K-fold target encode
# Get info on which patients belong to which fold
fold_patients = np.load(
os.path.join(
config["outputs"]["cohort_info_dir"],
"fold_patients_{}.npy".format(model_type),
),
allow_pickle=True,
)
train_encoded_cv, target_encodings = encoding.kfold_target_encode(
df=data,
fold_ids=fold_patients,
cols_to_encode=categorical_cols,
id_col="StudyId",
target="ExacWithin3Months",
smooth="auto",
drop_categorical_cols=False,
)
# Drop categorical cols except for AgeBinned as it is needed in imputation step
categorical_cols.remove("AgeBinned")
train_encoded = train_encoded.drop(columns=categorical_cols)
train_encoded_cv = train_encoded_cv.drop(columns=categorical_cols)
if (data_to_process == "test") | (data_to_process == "forward_val"):
# Encode test set/forward val set based on entire train set
target_encodings = json.load(
open("./data/artifacts/target_encodings_" + model_type + ".json")
)
test_encoded = encoding.apply_target_encodings(
data=data,
cols_to_encode=categorical_cols,
encodings=target_encodings,
drop_categorical_cols=False,
)
# Drop categorical cols except for AgeBinned as it is needed in imputation step
categorical_cols.remove("AgeBinned")
test_encoded = test_encoded.drop(columns=categorical_cols)
############################################################################
# Impute missing data
############################################################################
cols_to_ignore = [
"StudyId",
"PatientId",
"IndexDate",
"ExacWithin3Months",
"HospExacWithin3Months",
"CommExacWithin3Months",
"Age",
"Sex_F",
"SafeHavenID",
"AgeBinned",
]
if data_to_process == "train":
# Impute entire train set
not_imputed_train = train_encoded.copy()
cols_to_impute = train_encoded.drop(columns=cols_to_ignore).columns
imputer = imputation.get_imputer(
train_data=train_encoded,
cols_to_impute=cols_to_impute,
average_type="median",
cols_to_groupby=["AgeBinned", "Sex_F"],
)
imputed_train = imputation.apply_imputer(
data=train_encoded,
cols_to_impute=cols_to_impute,
imputer=imputer,
cols_to_groupby=["AgeBinned", "Sex_F"],
)
joblib.dump(imputer, "./data/artifacts/imputer_" + model_type + ".pkl")
# K-fold impute
not_imputed_train_cv = train_encoded_cv.copy()
imputed_train_cv = imputation.kfold_impute(
df=train_encoded,
fold_ids=fold_patients,
cols_to_impute=cols_to_impute,
average_type="median",
cols_to_groupby=["AgeBinned", "Sex_F"],
id_col="StudyId",
)
df_columns = imputed_train.columns.tolist()
if (data_to_process == "test") | (data_to_process == "forward_val"):
not_imputed_test = test_encoded.copy()
cols_to_impute = test_encoded.drop(columns=cols_to_ignore).columns
# Impute test set/forward val set based on entire train set
imputer = joblib.load("./data/artifacts/imputer_" + model_type + ".pkl")
imputed_test = imputation.apply_imputer(
data=test_encoded,
cols_to_impute=cols_to_impute,
imputer=imputer,
cols_to_groupby=["AgeBinned", "Sex_F"],
)
df_columns = imputed_test.columns.tolist()
############################################################################
# Reduce feature space
############################################################################
cols_to_drop_startswith = (
"DiffLatest",
"Var",
"LatestEQ5D",
"TotalEngagement",
"Age",
"NumHosp",
"Required",
"LungFunction",
"EngagementCAT",
"LatestSymptomDiary",
"LatestAlbumin",
"LatestEosinophils",
"LatestNeutrophils",
"LatestWhite Blood Count",
)
additional_cols_to_drop = [
"PatientId",
"SafeHavenID",
"Sex_F",
"NumCommExacPrior6mo",
"AsthmaOverlap",
"TimeSinceLungFunc",
"LatestNeutLymphRatio",
"EngagementEQ5DTW1",
"EngagementMRCTW1",
"LatestMRCQ1",
"WeekAvgCATQ1",
"WeekAvgCATQ3",
"WeekAvgCATQ4",
"WeekAvgCATQ5",
"WeekAvgCATQ6",
"WeekAvgCATQ7",
"WeekAvgCATQ8",
"WeekAvgSymptomDiaryQ1",
"WeekAvgSymptomDiaryQ3",
"WeekAvgSymptomDiaryScore",
"EngagementSymptomDiaryTW1",
"ScaledSumSymptomDiaryQ3TW1",
# "Comorbidities_te",
]
cols_to_drop = []
cols_to_drop.extend(
[item for item in df_columns if item.startswith(cols_to_drop_startswith)]
)
cols_to_drop.extend(additional_cols_to_drop)
if data_to_process == "train":
imputed_train = imputed_train.drop(columns=cols_to_drop)
not_imputed_train = not_imputed_train.drop(columns=cols_to_drop)
imputed_train_cv = imputed_train_cv.drop(columns=cols_to_drop)
not_imputed_train_cv = not_imputed_train_cv.drop(columns=cols_to_drop)
if (data_to_process == "test") | (data_to_process == "forward_val"):
imputed_test = imputed_test.drop(columns=cols_to_drop)
not_imputed_test = not_imputed_test.drop(columns=cols_to_drop)
############################################################################
# Save data
############################################################################
os.makedirs(config["outputs"]["model_input_data_dir"], exist_ok=True)
if data_to_process == "train":
imputed_train.to_pickle(
os.path.join(
config["outputs"]["model_input_data_dir"],
"{}_imputed_{}.pkl".format(data_to_process, model_type),
)
)
not_imputed_train.to_pickle(
os.path.join(
config["outputs"]["model_input_data_dir"],
"{}_not_imputed_{}.pkl".format(data_to_process, model_type),
)
)
imputed_train_cv.to_pickle(
os.path.join(
config["outputs"]["model_input_data_dir"],
"{}_imputed_cv_{}.pkl".format(data_to_process, model_type),
)
)
not_imputed_train_cv.to_pickle(
os.path.join(
config["outputs"]["model_input_data_dir"],
"{}_not_imputed_cv_{}.pkl".format(data_to_process, model_type),
)
)
if (data_to_process == "test") | (data_to_process == "forward_val"):
imputed_test.to_pickle(
os.path.join(
config["outputs"]["model_input_data_dir"],
"{}_imputed_{}.pkl".format(data_to_process, model_type),
)
)
not_imputed_test.to_pickle(
os.path.join(
config["outputs"]["model_input_data_dir"],
"{}_not_imputed_{}.pkl".format(data_to_process, model_type),
)
)
|