import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Read in the data and assign column names.
df = pd.read_csv(
    "weather-raw.csv",
    header=None,
    names=[
        "Timestamp",
        "Temperature",
        "Humidity",
        "Dew Point",
        "Pressure",
        "Wind Speed",
        "Wind Bearing",
        "Sunshine",
        "Rainfall",
        "Max Wind Speed",
    ],
)
# Rescale the values according to the documentation.
# Temperature -> deg C, Dew Point -> deg C, Wind Speed -> knots,
# Sunshine -> hours, Rainfall -> mm
scalings = {
    10: ["Temperature", "Dew Point", "Wind Speed", "Max Wind Speed"],
    100: "Sunshine",
    1000: "Rainfall",
}
for fac, cols in scalings.items():
    df[cols] = df.loc(axis=1)[cols] / fac

# Turn the index into a DateTimeIndex
df.index = pd.to_datetime(df["Timestamp"])

# -- (a) --
# Wind bearing is the cardinal direction the wind is blowing *to*.
modal_wind_bearing = df["Wind Bearing"].mode().values[0]
print("Most common wind bearing: {} deg".format(modal_wind_bearing))


# -- (b) --
# There is some obviously bad data indicating implausibly high wind speeds
# over a cluster of times in 2015: filter ths out.
df.loc[df["Max Wind Speed"] > 100, "Max Wind Speed"] = np.nan
idx = df["Max Wind Speed"].idxmax()
wind_max = df.loc[idx]["Max Wind Speed"]
print("Max wind speed: {} knots at {}".format(wind_max, idx))

# -- (c) --
sunshine_monthly = df["Sunshine"].resample("ME").sum()
idx = sunshine_monthly[sunshine_monthly.index.month == 6].idxmax()
print(
    "Greatest number of sunshine hours in a June: {:.1f} in {}".format(
        sunshine_monthly[idx], idx.year
    )
)

# -- (d) --
rain_daily = df["Rainfall"].resample("D").sum()
idx = rain_daily.idxmax()
print("Highest rainfall: {:.2f} mm on {}".format(rain_daily[idx], idx))

# -- (e) --
# There are different ways we could filter out the bad temperature data.
# Method 1: exclude data points nstd standard deviations away from the mean.
nstd = 3
tser = df["Temperature"].copy()
thresh = tser.mean() - nstd * tser.std()
tser[tser < thresh] = np.nan
idx = tser.idxmin()
print("Lowest temperature (method 1): {} deg C at {}".format(tser[idx], idx))

# Method 2: exclude data points from an identified date range.
df.loc["2015-10-15":"2016-01-15", "Temperature"] = np.nan
idx = df["Temperature"].idxmin()
print(
    "Lowest temperature (method 2): {} deg C at {}".format(
        df.loc[idx, "Temperature"], idx
    )
)