Delete analysis section of config.yaml

pull/95/head
Meng Li 2020-08-13 17:12:05 -04:00
parent 6fecb2f3db
commit 7a4218a3ce
1 changed files with 0 additions and 76 deletions

View File

@ -241,79 +241,3 @@ OVERALL_COMPLIANCE_HEATMAP:
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
### Example Analysis ################################################################
PARAMS_FOR_ANALYSIS:
COMPUTE: False
GROUNDTRUTH_TABLE: participant_info
TARGET_TABLE: participant_target
SOURCES: &sources ["phone_features", "fitbit_features", "phone_fitbit_features"]
DAY_SEGMENTS: *day_segments
PHONE_FEATURES: [accelerometer, activity_recognition, applications_foreground, battery, bluetooth, calls_incoming, calls_missed, calls_outgoing, conversation, light, location_doryab, messages_received, messages_sent, screen]
FITBIT_FEATURES: [fitbit_heartrate, fitbit_step, fitbit_sleep]
PHONE_FITBIT_FEATURES: "" # This array is merged in the input_merge_features_of_single_participant function in models.snakefile
DEMOGRAPHIC_FEATURES: [age, gender, inpatientdays]
CATEGORICAL_DEMOGRAPHIC_FEATURES: ["gender"]
FEATURES_EXCLUDE_DAY_IDX: False
# Whether or not to include only days with enough valid sensed hours
# logic can be found in rule phone_valid_sensed_days of rules/preprocessing.snakefile
DROP_VALID_SENSED_DAYS:
ENABLED: True
# Whether or not to include certain days in the analysis, logic can be found in rule days_to_analyse of rules/mystudy.snakefile
# If you want to include all days downloaded for each participant, set ENABLED to False
DAYS_TO_ANALYSE:
ENABLED: True
DAYS_BEFORE_SURGERY: 15
DAYS_IN_HOSPITAL: F # T or F
DAYS_AFTER_DISCHARGE: 7
# Cleaning Parameters
COLS_NAN_THRESHOLD: [0.1, 0.3, 0.5]
COLS_VAR_THRESHOLD: True
ROWS_NAN_THRESHOLD: [0.1, 0.3, 0.5]
PARTICIPANT_DAYS_BEFORE_THRESHOLD: 7
PARTICIPANT_DAYS_AFTER_THRESHOLD: 4
# Extract summarised features from daily features with any of the following substrings
NUMERICAL_OPERATORS: ["count", "sum", "length", "avg", "restinghr"]
CATEGORICAL_OPERATORS: ["mostcommon"]
MODEL_NAMES: ["LogReg", "kNN", "SVM", "DT", "RF", "GB", "XGBoost", "LightGBM"]
CV_METHODS: ["LeaveOneOut"]
SUMMARISED: ["summarised"] # "summarised" or "notsummarised"
RESULT_COMPONENTS: ["fold_predictions", "fold_metrics", "overall_results", "fold_feature_importances"]
MODEL_SCALER:
LogReg: ["notnormalized", "minmaxscaler", "standardscaler", "robustscaler"]
kNN: ["minmaxscaler", "standardscaler", "robustscaler"]
SVM: ["minmaxscaler", "standardscaler", "robustscaler"]
DT: ["notnormalized"]
RF: ["notnormalized"]
GB: ["notnormalized"]
XGBoost: ["notnormalized"]
LightGBM: ["notnormalized"]
MODEL_HYPERPARAMS:
LogReg:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__solver": ["newton-cg", "lbfgs", "liblinear", "saga"], "clf__penalty": ["l2"]}
kNN:
{"clf__n_neighbors": [1, 3, 5], "clf__weights": ["uniform", "distance"], "clf__metric": ["euclidean", "manhattan", "minkowski"]}
SVM:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__gamma": ["scale", "auto"], "clf__kernel": ["rbf", "poly", "sigmoid"]}
DT:
{"clf__criterion": ["gini", "entropy"], "clf__max_depth": [null, 3, 5, 7, 9], "clf__max_features": [null, "auto", "sqrt", "log2"]}
RF:
{"clf__n_estimators": [2, 5, 10, 100],"clf__max_depth": [null, 3, 5, 7, 9]}
GB:
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [5, 10, 100, 200], "clf__subsample": [0.5, 0.7, 1.0], "clf__max_depth": [3, 5, 7, 9]}
XGBoost:
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [5, 10, 100, 200], "clf__num_leaves": [5, 16, 31, 62]}
LightGBM:
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [5, 10, 100, 200], "clf__num_leaves": [5, 16, 31, 62]}
# Target Settings:
# 1 => TARGETS_RATIO_THRESHOLD (ceiling) or more of available CESD scores were TARGETS_VALUE_THRESHOLD or higher; 0 => otherwise
TARGETS_RATIO_THRESHOLD: 0.5
TARGETS_VALUE_THRESHOLD: 16