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

# # Gathering and Investigating Materials Project Data
# 
# This notebooks will show how you can use `requests` and `pandas` so gather and explore your data. Often times you will need to suply your data by other methods.
# 
# The `api` that we will be using is the material project. Link to the [api description](https://materialsproject.org/docs/api#materials_.28calculated_materials_data.29)
# 
# ![Materials Projnect](../images/materials_project.png)

# In[1]:


import requests

base_url = 'https://materialsproject.org/rest/v2/'


# # Getting Materials Project Api Key
# 
# This [link](https://www.materialsproject.org/open) details the steps necissary. 
# 
# 1. Visit [dashboard](https://materialsproject.org/dashboard) you may need to login
# 2. Generate API key if it has not already been generated and set `API_KEY` to this value.
# 
# The subprocess method is a way that I store my passwords on my computer and will not work for you.
# 
# Afterwards in the next cell we will test that our API key works. 
# 
# This is done by performing a `GET` or `POST` request to `https://www.materialsproject.org/rest/v1/api_check`.

# In[2]:


import subprocess
API_KEY = subprocess.check_output('gopass www/materialsproject.com apikey'.split()).decode('utf-8')
# API_KEY = "<apikey-here>"

session = requests.Session()
session.headers.update({'X-API-KEY': API_KEY})


# In[3]:


# for some reason the v2 API does not include an API check method??
response = session.get(f'https://www.materialsproject.org/rest/v1/api_check')
data = response.json()
print(data)

if not data['api_key_valid']:
    raise ValueError('You are not authenticated!')


# # Materials Project API
# 
# The materials project provides a RESTfull API for getting material properties which is detailed [here](https://www.materialsproject.org/docs/api#materials_.28calculated_materials_data.29).
# 
# If you have followed the steps above you should be ready to parse materials project data.
# 
# A RESTfull API is a nice way to expose data over the web. While they provide convenient methods for getting each individual material property they have a limit of 500 queries per day so we need to be efficient in our queries. To do this we will use the `npquery` to get properties in batch.
# 
# Lets start by getting a list of materials that are compossed of the following elements `Fe`, `Ti`, `O`, `C`, `N`, `He`. This does not affect your API limit

# In[20]:


def get_materials(elements):
    elements_str = '-'.join(elements)
    response = session.get(f'{base_url}/materials/{elements_str}/mids')
    data = response.json()
    print(f'Found {len(data["response"])} Materials in the Materials Project with the elements: {elements}')
    return data['response']

def get_material_experimental_properties(mid):
    response = session.get(f'{base_url}/materials/{mid}/exp/')
    print(response.content)
    data = response.json()['response'][0]
    print(data)
    return data

def get_material_vasp_properties(mid, piezoelectric=False, dielelectric=False):
    response = session.get(f'{base_url}/materials/{mid}/vasp/')
    material_data = response.json()['response'][0]
    
    if piezoelectric:
        response = session.get(f'{base_url}/materials/{mid}/vasp/piezo')
        data = response.json()
        if not data['valid_response']:
            material_data['piezoelectric'] = None
        else:
            material_data['piezoelectric'] = data['response']
        
    if dielelectric:
        response = session.get(f'{base_url}/materials/{mid}/vasp/diel')
        data = response.json()
        if not data['valid_response']:
            material_data['dielelectric'] = None
        else:
            material_data['dielelectric'] = data['response']
    
    return material_data


# In[27]:


material_ids = get_materials(['Fe', 'O', 'Ni', 'He', 'Zn', 'Cu'])


# # Basic VASP properties
# 
# Includes:
# 
#  - `energy`, `energy_per_atom`, `volume`, `formation_energy_per_atom`, `nsites`, `unit_cell_formula`, `pretty_formula`, `e_above_hull`, `spacegroup`, `icsd_ids`, `cif`, 
# 
#  - properties: `band_gap`, `density`, `energry`, `energy_per_atom`, `formation_energy_per_atom`, `elascticity`, `total_magnetization`
#  
# But some properties are still not included:
#   
#  -  `piezo`, `diel`

# In[86]:


# MgO

material_id = 'mp-1265'

# Na2O

material_id = 'mp-776952'


# In[26]:


data = get_material_vasp_properties(material_id, piezoelectric=True, dielelectric=True)
data.keys()


# # Basic Experimental properties
# 
# Turns out to be thermochemical data and not worth looking at

# In[ ]:


get_material_experimental_properties(material_id)


# # Let's gather the material data
# 
# The Material Project definently is not enforcing their `500` materials per day rate limit.
# 
# Also if you have a query that get greater than 3,000 materials it fails. Thus why some are commented out.

# In[29]:


materials_data = {}


# In[56]:


# Lets just grab a bunch of materials
material_ids = get_materials(['H', 'He', 
                              #'Li', 'Be', 
                              #'B', 'C', 'N', 
                              'O', 
                              #'F', 'Ne', 
                              #'Na', 'Mg', 'Al', 'Si', 'P', 'S', 'Cl', 'Ar'
                              'K', 'Ca', 
                              'Sc', 'Ti', 'V', 'Cr', 'Mn', 'Fe', 'Co', 'Ni', 'Cu', 'Zn',
                              # 'Ga', 'Ge', 'As', 'Se', 'Br', 'Kr',
                             ])
print('Number of materials', len(material_ids))


# In[57]:


# store the results
for mid in material_ids:
    if mid in materials_data:
        continue
    materials_data[mid] = get_material_vasp_properties(mid)


# In[58]:


len(materials_data)


# # Save all of the downloaded data to a json file

# In[59]:


import json


# In[60]:


json.dump(materials_data, open('mpdata.json', 'w'))


# In[61]:


get_ipython().system(' du -sh *')