#!/usr/bin/env python
# coding: utf-8

# # Map Trove newspaper results by place of publication over time
# 
# In [another notebook](Map-newspaper-results-by-place-of-publication.ipynb), I constructed a heatmap displaying the places of publication of articles returned by a search in Trove's newspapers zone.
# 
# I suggested that it would be interesting to visualise changes over time. This notebook does just that by creating an animated heatmap.
# 
# The key difference here is that instead of just getting and processing a single Trove API request, we'll need to fire off a series of API requests — one for each time interval.
# 
# You can use this notebook to visualise your own search queries, just edit the search parameters were indicated.
# 

# <div class="alert alert-block alert-warning">
# <p>If you haven't used one of these notebooks before, they're basically web pages in which you can write, edit, and run live code. They're meant to encourage experimentation, so don't feel nervous. Just try running a few cells and see what happens!.</p>
# 
# <p>
#     Some tips:
#     <ul>
#         <li>Code cells have boxes around them.</li>
#         <li>To run a code cell click on the cell and then hit <b>Shift+Enter</b>. The <b>Shift+Enter</b> combo will also move you to the next cell, so it's a quick way to work through the notebook.</li>
#         <li>While a cell is running a <b>*</b> appears in the square brackets next to the cell. Once the cell has finished running the asterix will be replaced with a number.</li>
#         <li>In most cases you'll want to start from the top of notebook and work your way down running each cell in turn. Later cells might depend on the results of earlier ones.</li>
#         <li>To edit a code cell, just click on it and type stuff. Remember to run the cell once you've finished editing.</li>
#     </ul>
# </p>
# </div>

# ## Setting things up
# 
# First we'll import the packages we need.

# In[13]:


# Import the libraries we need
import os

import folium
import pandas as pd
import requests
from folium.plugins import HeatMapWithTime
from IPython.display import display
from tqdm.auto import tqdm


# In[14]:


get_ipython().run_cell_magic('capture', '', '# Load variables from the .env file if it exists\n# Use %%capture to suppress messages\n%load_ext dotenv\n%dotenv\n')


# You need an [API key](http://help.nla.gov.au/trove/building-with-trove/api) to get data from Trove. Insert your key below.

# In[15]:


# Insert your Trove API key
API_KEY = "YOUR API KEY"

# Use api key value from environment variables if it is available
if os.getenv("TROVE_API_KEY"):
    API_KEY = os.getenv("TROVE_API_KEY")


# Set up some default parameters for our API query.

# In[16]:


# Set up default parameters for our API query
params = {
    "zone": "newspaper",
    "encoding": "json",
    "facet": "title",
    "n": "1",
    "key": API_KEY,
}

API_URL = "http://api.trove.nla.gov.au/v2/result"


# In[17]:


def format_facets(data):
    """
    Extract and normalise the facet data
    """
    # Check to make sure we have results
    try:
        facets = data["response"]["zone"][0]["facets"]["facet"]["term"]
    except TypeError:
        # No results!
        raise
    else:
        # Convert to DataFrame
        df = pd.DataFrame(facets)
        # Select the columns we want
        df = df[["display", "count"]]
        # Rename the columns
        df.columns = ["title_id", "total"]
        # Make sure the total column is a number
        df["total"] = pd.to_numeric(df["total"], errors="coerce")
    return df


def prepare_data(data):
    """
    Reformat the facet data, merge with locations, and then generate a list of locations.
    """
    # Check for results
    try:
        df = format_facets(data)
    except TypeError:
        # If there are no results just return and empty list
        hm_data = []
    else:
        # Merge facets data with geolocated list of titles
        df_located = pd.merge(df, locations, on="title_id", how="left")
        # Group results by place, and calculate the total results for each
        df_totals = df_located.groupby(["place", "latitude", "longitude"]).sum()
        hm_data = []
        for place in df_totals.index:
            # Get the total
            total = df_totals.loc[place]["total"]
            # Add the coordinates of the place to the list of locations as many times as there are articles
            hm_data += [[place[1], place[2]]] * total
    return hm_data


# Get the geolocated titles data
locations = pd.read_csv(
    "data/trove-newspaper-titles-locations.csv", dtype={"title_id": "int64"}
)
# Only keep the first instance of each title
locations.drop_duplicates(subset=["title_id"], keep="first", inplace=True)


# ## Construct your search
# 
# This is where you set your search keywords. Change 'weather AND wragge date:[* TO 1954]' in the cell below to anything you might enter in the Trove simple search box. Don't include a date range, as we'll be handling that separately. For example:
# 
# `params['q'] = 'weather AND wragge'`
# 
# `params['q'] = '"Clement Wragge"'`
# 
# `params['q'] = 'text:"White Australia Policy"'`
# 
# You can also limit the results to specific categories. To only search for articles, include this line:
# 
# `params['l-category'] = 'Article'`

# In[18]:


# Enter your search parameters
# This can be anything you'd enter in the Trove simple search box
params["q"] = 'text:"White Australia"'

# Remove the "#" symbol from the line below to limit the results to the article category
# params['l-category'] = 'Article'


# ## Set your date range
# 
# In this example we'll use years as our time interval. We could easily change this to months, or even individual days for a fine-grained analysis.

# In[19]:


start_year = 1880
end_year = 1950


# ## Get the data from Trove
# 
# We need to make an API request for each year in our date range, so we'll construct a loop.
# 
# The cell below generates two lists. The first, `hm_series`, is a list containing the data from each API request. The second, `time_index`, is a list of the years we're getting data for. Obviously these two lists should be the same length — one dataset for each year.

# In[ ]:


# <-- Click the run icon
hm_series = []
time_index = []
for year in tqdm(range(start_year, end_year + 1)):
    time_index.append(year)
    decade = str(year)[:3]
    params["l-decade"] = decade
    params["l-year"] = year
    response = requests.get(API_URL, params=params)
    data = response.json()
    hm_data = prepare_data(data)
    hm_series.append(hm_data)


# ## Make an animated heatmap
# 
# To create an animated heatmap we just need to feed it the `hm_series` data and time index.

# In[21]:


# <-- Click the run icon
# Create the map
m = folium.Map(location=[-30, 135], zoom_start=4)

# Add the heatmap data!
HeatMapWithTime(hm_series, index=time_index, auto_play=True).add_to(m)


# ### Search for "White Australia" from 1880 to 1950

# In[22]:


# <-- Click the run icon
display(m)


# ----
# 
# Created by [Tim Sherratt](https://timsherratt.org/) for the [GLAM Workbench](https://glam-workbench.github.io/).  
# Support this project by becoming a [GitHub sponsor](https://github.com/sponsors/wragge?o=esb).