import argparse
import pandas as pd
from typing import Optional
from pydantic import BaseModel, field_validator, ValidationError
from datetime import datetime
# Define the Pydantic model for sleep data
class SleepData(BaseModel):
cycle_start_time: datetime | None
cycle_end_time: datetime | None
cycle_timezone: str
sleep_onset: datetime
wake_onset: datetime
sleep_performance: int
respiratory_rate: float
asleep_duration: int
in_bed_duration: int
light_sleep_duration: int
deep_sws_duration: int
rem_duration: int
awake_duration: int
sleep_need: int
sleep_debt: int | None
sleep_efficiency: int
sleep_consistency: int | None
nap: bool
# Validator for boolean fields represented as 'true/false' in the CSV
@field_validator("nap", mode="before")
def parse_boolean(cls, value):
if isinstance(value, bool):
return value
return value.lower() == "true"
# Validator to handle optional fields with NaN values
@field_validator("cycle_end_time", "sleep_consistency", mode="before")
def handle_optional_nan(cls, value):
if pd.isna(value):
return None
return value
def to_dict(self):
"""Convert the model instance to a dictionary."""
return self.dict()
def read_and_parse_csv(file_path: str):
"""Read the sleeps.csv file and parse it using the SleepData model."""
try:
# Read the CSV file into a Pandas DataFrame
df = pd.read_csv(file_path)
# Rename columns to match the Pydantic model's attributes
df.columns = [
"cycle_start_time",
"cycle_end_time",
"cycle_timezone",
"sleep_onset",
"wake_onset",
"sleep_performance",
"respiratory_rate",
"asleep_duration",
"in_bed_duration",
"light_sleep_duration",
"deep_sws_duration",
"rem_duration",
"awake_duration",
"sleep_need",
"sleep_debt",
"sleep_efficiency",
"sleep_consistency",
"nap",
]
# Parse each row using the Pydantic model
sleep_data = []
for row in df.to_dict(orient="records"):
try:
sleep_data.append(SleepData(**row))
except ValidationError as e:
print(f"Validation error for row {row}: {e}")
return sleep_data
except Exception as e:
print(f"Error parsing the CSV file: {e}")
return []
def generate_html_report(sleep_data, output_file):
"""Generate an HTML report with two graphs."""
dates = [data.sleep_onset.strftime("%Y-%m-%d") for data in sleep_data]
rem_durations = [data.rem_duration for data in sleep_data]
# Reverse the order of dates and REM durations for chronological display
dates.reverse()
rem_durations.reverse()
# Calculate monthly averages
df = pd.DataFrame({"date": dates, "rem_duration": rem_durations})
df["date"] = pd.to_datetime(df["date"])
df["month"] = df["date"].dt.to_period("M")
monthly_avg = df.groupby("month")["rem_duration"].mean()
# Convert to JavaScript-friendly formats
monthly_avg_labels = [str(month) for month in monthly_avg.index]
monthly_avg_values = [
float(value) for value in monthly_avg.values
] # Convert np.float64 to float
html_template = f"""
Sleep Data Report
Sleep Data Report
Daily REM Durations
Monthly Average REM Durations
"""
with open(output_file, "w") as file:
file.write(html_template)
def main():
parser = argparse.ArgumentParser(
description="Parse and validate a sleeps.csv file."
)
parser.add_argument("file", type=str, help="Path to the sleeps.csv file")
parser.add_argument("output", type=str, help="Path to the output HTML file")
args = parser.parse_args()
sleep_data = read_and_parse_csv(args.file)
if sleep_data:
print("Generating HTML report...")
generate_html_report(sleep_data, args.output)
print(f"Report generated: {args.output}")
else:
print("No valid data found in the file.")
if __name__ == "__main__":
main()