Daily Weather Data

class Daily:
    def __init__(self, loc: Union[pd.DataFrame, Point, list, str], start=datetime(1781, 1, 1, 0, 0, 0), end=datetime.combine(datetime.today().date() + timedelta(days=10), datetime.max.time()), model=True, flags=False) -> None:
        """
        Initialize daily weather data retrieval.
        
        Parameters:
        - loc: Union[pd.DataFrame, Point, list, str]
            - pd.DataFrame: Station data from Stations.fetch()
            - Point: Geographic point for automatic station selection
            - list: List of station IDs
            - str: Single station ID
        - start: datetime, start of time period (default: 1781-01-01)
        - end: datetime, end of time period (default: 10 days from today)
        - model: bool, whether to include model/reanalysis data (default: True)
        - flags: bool, whether to include data source flags (default: False)
        """

def expected_rows(self) -> int:
    """
    Return expected number of daily rows for the date range.
    
    Returns:
    int, expected number of daily observations
    """

# Temperature measurements (°C)
tavg: float       # Average temperature
tmin: float       # Minimum temperature  
tmax: float       # Maximum temperature

# Precipitation
prcp: float       # Total precipitation amount (mm)

# Snow and winter weather
snow: float       # Snow depth (mm)

# Wind measurements  
wdir: float       # Prevailing wind direction (degrees, 0-360)
wspd: float       # Average wind speed (km/h)
wpgt: float       # Peak wind gust (km/h)

# Atmospheric pressure
pres: float       # Average sea level pressure (hPa)

# Solar radiation
tsun: float       # Total sunshine duration (minutes)

# Data quality flags (when flags=True)
tavg_flag: str    # Average temperature data source flag
tmin_flag: str    # Minimum temperature data source flag
tmax_flag: str    # Maximum temperature data source flag
# ... (additional _flag columns for each parameter)

from datetime import datetime
from meteostat import Point, Daily

# Set time period for 2020
start = datetime(2020, 1, 1)
end = datetime(2020, 12, 31)

# Create point for London, UK
london = Point(51.5074, -0.1278, 11)

# Get daily data
data = Daily(london, start, end)
daily_data = data.fetch()

print(f"Retrieved {len(daily_data)} daily observations")
print(daily_data[['tavg', 'tmin', 'tmax', 'prcp']].head())

from datetime import datetime
from meteostat import Stations, Daily

# Get stations with long historical records
stations = Stations().region('GB').inventory('daily', True).fetch(5)

# Analyze temperature trends over 50 years
start = datetime(1970, 1, 1)
end = datetime(2020, 12, 31)

data = Daily(stations, start, end)
historical_data = data.fetch()

# Calculate annual averages
annual_temps = historical_data.groupby(historical_data.index.year)['tavg'].mean()
print("50-year temperature trend:")
print(annual_temps.head(10))

from datetime import datetime
from meteostat import Point, Daily
import pandas as pd

# Analyze seasonal patterns for Chicago
chicago = Point(41.8781, -87.6298, 182)

# Get 10 years of data
start = datetime(2010, 1, 1)
end = datetime(2019, 12, 31)

data = Daily(chicago, start, end)
daily_data = data.fetch()

# Calculate seasonal averages
daily_data['season'] = daily_data.index.month.map({
    12: 'Winter', 1: 'Winter', 2: 'Winter',
    3: 'Spring', 4: 'Spring', 5: 'Spring',
    6: 'Summer', 7: 'Summer', 8: 'Summer',
    9: 'Fall', 10: 'Fall', 11: 'Fall'
})

seasonal_stats = daily_data.groupby('season').agg({
    'tavg': 'mean',
    'tmin': 'mean', 
    'tmax': 'mean',
    'prcp': 'sum'
})

print("Seasonal climate summary for Chicago:")
print(seasonal_stats)

from datetime import datetime
from meteostat import Stations, Daily

# Compare daily temperatures across multiple cities
city_stations = Stations().nearby(40.7128, -74.0060, 10000).fetch(1)  # NYC
city_stations = city_stations.append(Stations().nearby(34.0522, -118.2437, 10000).fetch(1))  # LA

# Get summer 2020 data
start = datetime(2020, 6, 1)
end = datetime(2020, 8, 31)

data = Daily(city_stations, start, end)
city_data = data.fetch()

# Compare average temperatures by station
temp_comparison = city_data.groupby('station')[['tavg', 'tmin', 'tmax']].mean()
print("Summer 2020 temperature comparison:")
print(temp_comparison)

from datetime import datetime  
from meteostat import Point, Daily

# Analyze precipitation patterns for Seattle
seattle = Point(47.6062, -122.3321, 56)

# Get recent year of data
start = datetime(2020, 1, 1)
end = datetime(2020, 12, 31)

data = Daily(seattle, start, end)  
daily_data = data.fetch()

# Precipitation statistics
rainy_days = (daily_data['prcp'] > 0).sum()
total_precip = daily_data['prcp'].sum()
max_daily_precip = daily_data['prcp'].max()

print(f"Seattle 2020 precipitation summary:")
print(f"Rainy days: {rainy_days}")
print(f"Total precipitation: {total_precip:.1f} mm")
print(f"Maximum daily precipitation: {max_daily_precip:.1f} mm")

# Source flag meanings for daily data
"A": str  # High-quality daily observations from national weather services
"B": str  # GHCN-D global historical climatology network data
"C": str  # Aggregated from high-quality hourly observations
"D": str  # ISD Lite aggregated observations
"E": str  # SYNOP aggregated observations  
"F": str  # METAR aggregated aviation reports
"G": str  # Model/reanalysis data (ERA5, GFS, etc.)

# Analyze precipitation patterns
wet_days = daily_data[daily_data['prcp'] > 0.1]  # Days with measurable precipitation
dry_spells = daily_data[daily_data['prcp'] == 0]  # Dry days

# Data retrieval and analysis
def fetch(self) -> pd.DataFrame: ...
def count(self) -> int: ...
def coverage(self): ...

# Data processing  
def normalize(self): ...
def interpolate(self, limit: int = 3): ...
def aggregate(self, freq: str, spatial: bool = False): ...
def convert(self, units: dict): ...

# Utility methods
def stations(self) -> pd.Index: ...
def clear_cache(self): ...

# Aggregate to monthly values
monthly_data = daily_data.aggregate('MS')  # Month start frequency

# Aggregate to annual values  
annual_data = daily_data.aggregate('AS')   # Year start frequency

# Custom aggregations with spatial averaging
regional_monthly = daily_data.aggregate('MS', spatial=True)