junos
/
stress_at_work_analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[WIP] Separate the features part from the pipeline.

rapids
junos 2021-08-16 18:11:25 +02:00
parent d6f36ec8f8
commit 3821314dd9
1 changed files with 72 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

107
machine_learning/pipeline.py
View File

@ -8,6 +8,53 @@ from features import esm, helper, proximity
from machine_learning import QUESTIONNAIRE_IDS, QUESTIONNAIRE_IDS_RENAME
class SensorFeatures:
def __init__(
self,
grouping_variable,
data_types,
feature_names=None,
participants_usernames=None,
):
self.data_types = data_types
self.grouping_variable = grouping_variable
if feature_names is None:
self.feature_names = []
if participants_usernames is None:
participants_usernames = participants.query_db.get_usernames(
collection_start=datetime.date.fromisoformat("2020-08-01")
)
self.participants_usernames = participants_usernames
self.df_proximity = pd.DataFrame()
self.df_proximity_counts = pd.DataFrame()
def set_sensor_data(self):
if "proximity" in self.data_types:
self.df_proximity = proximity.get_proximity_data(
self.participants_usernames
)
self.df_proximity = helper.get_date_from_timestamp(self.df_proximity)
self.df_proximity = proximity.recode_proximity(self.df_proximity)
def get_sensor_data(self, data_type) -> pd.DataFrame:
# TODO implement the getter (Check if it has been set.)
return self.df_proximity
def calculate_features(self):
if "proximity" in self.data_types:
self.df_proximity_counts = proximity.count_proximity(
self.df_proximity, ["participant_id", self.grouping_variable]
)
# TODO Think about joining dataframes.
def get_features(self, data_type) -> pd.DataFrame:
# TODO implement the getter (Check if it has been set.)
return self.df_proximity_counts
class MachineLearningPipeline:
def __init__(
self,
@ -42,8 +89,6 @@ class MachineLearningPipeline:
self.df_esm_interest = pd.DataFrame()
self.df_esm_clean = pd.DataFrame()
self.df_proximity = pd.DataFrame()
self.df_full_data_daily_means = pd.DataFrame()
self.df_esm_daily_means = pd.DataFrame()
self.df_proximity_daily_counts = pd.DataFrame()
@ -64,39 +109,31 @@ class MachineLearningPipeline:
]
self.df_esm_clean = esm.clean_up_esm(self.df_esm_interest)
def get_sensor_data(self):
if "proximity" in self.data_types:
self.df_proximity = proximity.get_proximity_data(
self.participants_usernames
)
self.df_proximity = helper.get_date_from_timestamp(self.df_proximity)
self.df_proximity = proximity.recode_proximity(self.df_proximity)
def aggregate_daily(self):
self.df_esm_daily_means = (
self.df_esm_clean.groupby(["participant_id", "date_lj", "questionnaire_id"])
.esm_user_answer_numeric.agg("mean")
.reset_index()
.rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
)
self.df_esm_daily_means = (
self.df_esm_daily_means.pivot(
index=["participant_id", "date_lj"],
columns="questionnaire_id",
values="esm_numeric_mean",
)
.reset_index(col_level=1)
.rename(columns=QUESTIONNAIRE_IDS_RENAME)
.set_index(["participant_id", "date_lj"])
)
self.df_full_data_daily_means = self.df_esm_daily_means.copy()
if "proximity" in self.data_types:
self.df_proximity_daily_counts = proximity.count_proximity(
self.df_proximity, ["participant_id", "date_lj"]
)
self.df_full_data_daily_means = self.df_full_data_daily_means.join(
self.df_proximity_daily_counts
)
# def aggregate_daily(self):
# self.df_esm_daily_means = (
# self.df_esm_clean.groupby(["participant_id", "date_lj", "questionnaire_id"])
# .esm_user_answer_numeric.agg("mean")
# .reset_index()
# .rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
# )
# self.df_esm_daily_means = (
# self.df_esm_daily_means.pivot(
# index=["participant_id", "date_lj"],
# columns="questionnaire_id",
# values="esm_numeric_mean",
# )
# .reset_index(col_level=1)
# .rename(columns=QUESTIONNAIRE_IDS_RENAME)
# .set_index(["participant_id", "date_lj"])
# )
# self.df_full_data_daily_means = self.df_esm_daily_means.copy()
# if "proximity" in self.data_types:
# self.df_proximity_daily_counts = proximity.count_proximity(
# self.df_proximity, ["participant_id", "date_lj"]
# )
# self.df_full_data_daily_means = self.df_full_data_daily_means.join(
# self.df_proximity_daily_counts
# )
def assign_columns(self):
self.df_features = self.df_full_data_daily_means[self.feature_names]