import pandas as pd
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
import chart_studio.plotly as py
import plotly.graph_objects as go
init_notebook_mode(connected=False)
import plotly.express as px
import numpy as np
import seaborn as sns
import string
import glob
import plotly.io as pio

#You will need your own token
token = open(".mapbox_token").read() 

places = pd.read_csv("acorn_sat_v2.1.0_stations.csv")
places.head()

#Loop through the weather station CSVs, run some preprocessing and add the dataframes to a temporary list
path = "max"
li = []
 
for count, f in enumerate(glob.glob(path + "/*.csv")):
    df = pd.read_csv(f, index_col=None, header=0)
    df['site number'] = df['site number'][0]
    df['site name'] = string.capwords(df['site name'][0])
    df['lat'] = places['lat'][count]
    df['lon'] = places['lon'][count]
    df = df.drop(df.index[0])
    df['year'] = pd.to_datetime(df['date']).dt.year
    df['long term average'] = df['maximum temperature (degC)'][(df['year']<1980) & (df['year']>1949)].mean()
    li.append(df)

#Concatenate list of dataframes into one large dataframe of nearly 4 million rows. 
df = pd.concat(li, axis=0, ignore_index=True)

#Do likewise with the weather station data from the 'min' dataset
path = "min"
li = []

for count, f in enumerate(glob.glob(path + "/*.csv")):
    df_min = pd.read_csv(f, index_col=None, header=0)
    df_min = df_min.drop(df_min.index[0])
    li.append(df_min)

df_min = pd.concat(li, axis=0, ignore_index=True)

#Add the minimum temperature data to the first dataframe
df['min'] = df_min['minimum temperature (degC)']
df.rename(columns = {"maximum temperature (degC)": "max"}, inplace=True)

df['date'] = pd.to_datetime(df['date'])
df['year'] = pd.to_datetime(df['date']).dt.year

df.head()

df.dtypes

df.describe(include=[np.object])

pd.isnull(df['max']).value_counts()

dfheat = df.copy()

#Tag days where the temperature reading exceeded 40°C (104 °F)
dfheat['Average Days of 40C+ / Year'] = np.where(dfheat['max'] >= 40, 1, 0)

dfheat.head()

#Slice dataframe and select the top 10 locations
df_hottest = dfheat[dfheat['year'] == 2019]
df_hottest = df_hottest.groupby(["site name"]).sum()
df_hottest = df_hottest.sort_values('Average Days of 40C+ / Year', ascending=False)
df_hottest = df_hottest.reset_index().loc[:9, :]

df_hottest

#Create barchart visualisation using Plotly

colors = ['lightsalmon',] * 10
colors[0] = 'indianred'

fig = go.Figure([go.Bar(x=df_hottest['site name'], y=df_hottest["Average Days of 40C+ / Year"], marker_color=colors)])

fig.update_yaxes(title="Count")
fig.update_layout(title_text= "Australia's Hottest Towns: Most Frequent Days Over 40°C (104 °F)", height=450, width=800)


fig.show()

#Group dataframe by year and obtain average of days over 40C across weather stations
dfheat = dfheat.groupby([pd.Grouper(key="date", freq="Y")]).mean()*365
dfheat = dfheat.reset_index()
dfheat['year'] = dfheat['date'].dt.year

#Select records from 1950 to present
dfheat = dfheat[dfheat['year'] >= 1950]

dfheat.head()

#Visualise the data
fig = px.bar(dfheat, x="year", y="Average Days of 40C+ / Year",
            hover_data=['year', 'Average Days of 40C+ / Year'], 
             color_continuous_scale="hot_r",
             color='Average Days of 40C+ / Year',
             labels={'year':'Year', 'Average Days of 40C+ / Year': "Count"}, height=450)
fig.update_layout(title_text="Australia Average Days of 40°C+ (104°F) / Year")

fig.show()

#Set dataframe date range and group by 3 months
start = '1950-08-01'
end = '2019-12-31'
mask = (df['date'] > start) & (df['date'] <= end)
df_seasons = (
    df.loc[mask]
    .groupby(pd.Grouper(freq="3M", key="date"))
    .mean()
    .iloc[::2]
    .reset_index()
)
#Label grouped months as seasons
df_seasons.loc[1::2, 'season'] = 'Summer'
df_seasons.loc[::2, 'season'] = 'Winter'

#Create temperature range column & year column
df_seasons.loc[:, 'temp_range'] = df_seasons['max'] - df_seasons['min']
df_seasons.loc[:, 'year'] = pd.DatetimeIndex(df_seasons['date']).year

df_seasons.head()

oni_values = pd.read_csv("ONI Values.csv", skiprows=2)
oni_values.head()

#The ONI scores are now added to the corresponding season in the df_seasons dataframe
for count, f in enumerate(oni_values.values):
    df_seasons.loc[count*2, "oni_value"] = float(f[4])
    df_seasons.loc[count*2+1, "oni_value"] = float(f[10])

df_seasons = df_seasons.dropna()

#Create a scatterplot
fig = px.scatter(df_seasons, x="year", y="max", facet_row="season", opacity=1, 
                 labels=dict(year="Year", difference="Average Daily Temperature Range (°C)", oni_value='Oceanic Niño Index'),
                 trendline = "ols", trendline_color_override="red", color="oni_value", color_continuous_scale='bluered')

fig.update_layout(height=600, width=1000, title_text="Australian Seasonal Average Daily Temperature (1950-2020)")

fig.update_xaxes(nticks=10)
fig.update_yaxes(nticks=10, title_text="Temperature (°C)", matches=None)

fig.show()

#Create a scatterplot showing average daily temperature range for Summer and one for Winter
fig = px.scatter(df_seasons, x="year", y="temp_range", facet_row="season", opacity=1, 
                 labels=dict(year="Year", temp_range="Temperature Range (°C)"),
                 trendline = "ols", trendline_color_override="red")

fig.update_layout(height=600, width=1000, title_text="Australian Average Daily Temperature Range (1950-2020)")

fig.update_xaxes(nticks=10)
fig.update_yaxes(nticks=10, matches=None)

fig.show()
pio.write_html(fig, file='figure4.html', auto_open=True)

#Consolidate dataframe into yearly average temperatures and group by location.
dfyear = df.copy()[df['year'] >= 1950].groupby(['site name', pd.Grouper(key="date", freq="Y")]).mean()

#Using the long term average for each location between 1950-1980, we can calculate the difference in temperature for each year & location.
dfyear = (
    dfyear.dropna(subset=['max']).
    reset_index()
)
dfyear.loc[:,'+/- Long Term Average'] = (dfyear['max']-dfyear['long term average'])
dfyear = dfyear.round(1)

dfyear.head()

fig = px.scatter_mapbox(dfyear, lat="lat", 
                        lon="lon", 
                        size="max",
                        size_max = 20,
                        hover_name="site name", 
                        hover_data=["max","min"],
                        color="+/- Long Term Average",
                        color_continuous_scale="blackbody_r", 
                        range_color =[-2,3],
                        zoom=3.8, height=800, width=1000, 
                        animation_frame="year", 
                        )
fig.update_layout(
    mapbox_style="satellite",
    mapbox_accesstoken=token,
        title={
        'text': 'AUS Surface Temperature 1950-2019<br>Source: <a href="http://www.bom.gov.au/climate/data-services/station-data.shtml">BoM</a>',
        'y':0.3,
        'x':0.05,
        'xanchor': 'left',
        'yanchor': 'top'},
        font=dict(
            color="grey",
        )
)

#Adjust pitch and bearing to adjust the rotation
fig.update_layout(margin={"r":0,"t":20,"l":0,"b":20},
                  mapbox=dict(
                      pitch=40,
                      bearing=0,
                      center=dict(
                      lat=-31,
                      lon = 134),
                  ),


                 )
fig.show()