ML with RAPIDS and missing values.

rapids
junos 2022-01-19 12:53:03 +01:00
parent 702b091d73
commit 832eb6137e
1 changed files with 94 additions and 12 deletions

View File

@ -27,6 +27,7 @@ import yaml
from pyprojroot import here
from sklearn import linear_model
from sklearn.model_selection import LeaveOneGroupOut, cross_val_score
from sklearn.impute import SimpleImputer
nb_dir = os.path.split(os.getcwd())[0]
if nb_dir not in sys.path:
@ -266,33 +267,114 @@ with open(here("rapids/config.yaml"), "r") as file:
rapids_config = yaml.safe_load(file)
# %%
for key in rapids_config.keys():
for key in rapids_config.keys():
if isinstance(rapids_config[key], dict): # Remove top-level configs
if "PROVIDERS" in rapids_config[key]: # Retain features (that have providers)
if ("PROVIDERS" in rapids_config[key]): # Retain features (that have providers)
if rapids_config[key]["PROVIDERS"]: # Remove non-implemented features
for provider in rapids_config[key]["PROVIDERS"]:
if rapids_config[key]["PROVIDERS"][provider][
"COMPUTE"
]: # Check that the features were actually calculated
if rapids_config[key]["PROVIDERS"][provider]["COMPUTE"]: # Check that the features were actually calculated
if "FEATURES" in rapids_config[key]["PROVIDERS"][provider]:
print(key)
print(provider)
print(rapids_config[key]["PROVIDERS"][provider]["FEATURES"])
# %%
features_rapids = pd.read_csv(
here("rapids/data/processed/features/all_participants/all_sensor_features.csv"),
parse_dates=["local_segment_start_datetime", "local_segment_end_datetime"],
)
features_rapids = pd.read_csv(here("rapids/data/processed/features/all_participants/all_sensor_features.csv"), parse_dates=["local_segment_start_datetime", "local_segment_end_datetime"])
# %%
features_rapids.columns
# %%
features_rapids = features_rapids.assign(
date_lj=lambda x: x.local_segment_start_datetime.dt.date
)
features_rapids = features_rapids.assign(date_lj=lambda x: x.local_segment_start_datetime.dt.date)
# %%
features_rapids["participant_id"] = features_rapids["pid"].str.extract("(\d+)")
features_rapids["participant_id"] = pd.to_numeric(features_rapids["participant_id"])
features_rapids.set_index(["participant_id", "date_lj"], inplace=True)
# %%
with open("../machine_learning/config/minimal_labels.yaml", "r") as file:
labels_params = yaml.safe_load(file)
# %%
labels = machine_learning.labels.Labels(**labels_params)
labels.set_participants_label("all")
# %%
labels.aggregate_labels(cached=True)
labels_read = labels.get_aggregated_labels()
labels_read = labels_read.reset_index()
labels_read["date_lj"] = labels_read["date_lj"].dt.date
labels_read.set_index(["participant_id", "date_lj"], inplace=True)
# date_lj column is parsed as a date and represented as Timestamp, when read from csv.
# When calculated, it is represented as date.
# %%
features_rapids.shape
# %%
labels_read.shape
# %%
features_labels = features_rapids.join(labels_read, how="inner").reset_index()
# %%
features_labels.shape
# %%
features_labels.columns
# %%
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
# %%
feature_columns = features_labels.columns[6:-3]
label_column = "NA"
group_column = "pid"
# %%
lin_reg_rapids = linear_model.LinearRegression()
logo = LeaveOneGroupOut()
logo.get_n_splits(
features_labels[feature_columns],
features_labels[label_column],
groups=features_labels[group_column],
)
# %%
cross_val_score(
lin_reg_rapids,
X=imputer.fit_transform(features_labels[feature_columns]),
y=features_labels[label_column],
groups=features_labels[group_column],
cv=logo,
n_jobs=-1,
scoring="r2",
)
# %%
sns.set(rc={"figure.figsize":(16, 8)})
sns.heatmap(features_labels[feature_columns].isna(), cbar=False)
# %% [markdown] tags=[]
# ```yaml
# ALL_CLEANING_INDIVIDUAL:
# PROVIDERS:
# RAPIDS:
# COMPUTE: True
# IMPUTE_SELECTED_EVENT_FEATURES: # Fill NAs with 0 only for event-based features, see table below
# COMPUTE: True
# MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 # Any feature value in a time segment instance with phone data yield > [MIN_DATA_YIELDED_MINUTES_TO_IMPUTE] will be replaced with a zero.
# COLS_NAN_THRESHOLD: 0.3 # Discard columns with missing value ratios higher than [COLS_NAN_THRESHOLD]. Set to 1 to disable
# COLS_VAR_THRESHOLD: True # Set to True to discard columns with zero variance
# ROWS_NAN_THRESHOLD: 1 # Discard rows with missing value ratios higher than [ROWS_NAN_THRESHOLD]. Set to 1 to disable
# DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
# DATA_YIELD_RATIO_THRESHOLD: 0.3 # Discard rows with ratiovalidyieldedhours or ratiovalidyieldedminutes feature less than [DATA_YIELD_RATIO_THRESHOLD]. The feature name is determined by [DATA_YIELD_FEATURE] parameter. Set to 0 to disable
# DROP_HIGHLY_CORRELATED_FEATURES:
# COMPUTE: False
# MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
# CORR_THRESHOLD: 0.95
# SRC_SCRIPT: src/features/all_cleaning_individual/rapids/main.R
# ```
# %%