Update histogram of phone data yield

pull/147/head
Meng Li 2021-06-17 12:27:32 -04:00
parent f436f1f530
commit e98a8ff7ca
2 changed files with 8 additions and 0 deletions

View File

@ -1,6 +1,8 @@
rule histogram_phone_data_yield: rule histogram_phone_data_yield:
input: input:
"data/processed/features/all_participants/all_sensor_features.csv" "data/processed/features/all_participants/all_sensor_features.csv"
params:
time_segments_type = config["TIME_SEGMENTS"]["TYPE"]
output: output:
"reports/data_exploration/histogram_phone_data_yield.html" "reports/data_exploration/histogram_phone_data_yield.html"
script: script:

View File

@ -2,8 +2,14 @@ import pandas as pd
import plotly.express as px import plotly.express as px
time_segments_type = snakemake.params["time_segments_type"]
phone_data_yield = pd.read_csv(snakemake.input[0]) phone_data_yield = pd.read_csv(snakemake.input[0])
if time_segments_type == "FREQUENCY":
phone_data_yield["local_segment_label"] = phone_data_yield["local_segment_label"].str.split("\d+", expand=True, n=1)[0]
if time_segments_type == "EVENT":
phone_data_yield["local_segment_label"] = "event"
# make sure the input file contains "phone_data_yield_rapids_ratiovalidyieldedminutes" and "phone_data_yield_rapids_ratiovalidyieldedhours" columns # make sure the input file contains "phone_data_yield_rapids_ratiovalidyieldedminutes" and "phone_data_yield_rapids_ratiovalidyieldedhours" columns
if ("phone_data_yield_rapids_ratiovalidyieldedminutes" not in phone_data_yield.columns) or ("phone_data_yield_rapids_ratiovalidyieldedhours" not in phone_data_yield.columns): if ("phone_data_yield_rapids_ratiovalidyieldedminutes" not in phone_data_yield.columns) or ("phone_data_yield_rapids_ratiovalidyieldedhours" not in phone_data_yield.columns):
raise ValueError("Please make sure [PHONE_DATA_YIELD][RAPIDS][COMPUTE] is True AND [PHONE_DATA_YIELD][RAPIDS][FEATURES] contains [ratiovalidyieldedminutes, ratiovalidyieldedhours].") raise ValueError("Please make sure [PHONE_DATA_YIELD][RAPIDS][COMPUTE] is True AND [PHONE_DATA_YIELD][RAPIDS][FEATURES] contains [ratiovalidyieldedminutes, ratiovalidyieldedhours].")