Mongo Loves Data post 1 - From Atlas to Compass to Graphs

call-python.R

#
#  SETUP:  
#      python:
#      python-example.py has the following dependencies
#      pymongo, pandas, dnspython

#     R
#        reticulate, ggplot2, dplyr, ggmap, leaflet

LONG = -73.730564
LAT =  40.6737
DISTANCE = 1500

library( reticulate)
library(ggplot2)
library( dplyr )
use_python('/usr/local/bin/python3')
source_python( 'python-example.py')
data <- python_script(c(LONG, LAT), DISTANCE)
#
#  Use dply to add colums with displayable names
#   then plot with ggplot
#
grph <-  data.frame(data[1]) %>% mutate( Cusine=X_id, Count=count) %>% ggplot( aes(X_id, Count)) +
geom_col(aes( fill=Cusine)) + labs(title='Restaurants within 1.5 km', x='Cusine', y='Count') +
theme( axis.text.x=element_blank())



 
# Spatial graph see https://rpubs.com/jhofman/nycma
library(leaflet)
library(sp)
library(ggmap)
library(broom)

m <- leaflet() %>%
  addTiles() %>%
  setView(LONG, LAT, zoom = 13)

# data is an array, second member is  a list of restaurants with coords
d <- data.frame( data[2]) %>% select( lng, lat, name)
m %>% addMarkers(d, lng=d$lng, lat = d$lat, popup = d$name ) %>%
  addCircles(LONG, LAT, radius=DISTANCE, color = 'yellow') %>%
  addCircles(LONG, LAT, radius=30, color = 'red', popup="YOU ARE HERE")

python_exampl.py

# make sure you have pymongo and pandas installed - I used pip

from pymongo import MongoClient
import pandas as pd
from os import environ

SECRET = environ["secret_pwd"]
USER = environ['secret_user']


# set defaults  on the function
# set defaults  on the function
def python_script(coord=[-73.730564, 40.67372], distance = 1500):
 
    # geoNear takes a point and finds all data records within a given distance
    # https://docs.mongodb.com/manual/reference/operator/aggregation/geoNear/#mongodb-pipeline-pipe.-geoNear
    # facet creats two or more intermediate pipelines, in this case a summary and  listing objects
    # Requires the PyMongo package.
    # https://api.mongodb.com/python/current



    client = MongoClient(
        # this isn't a valid user/pwd combo
        'mongodb+srv://'+ USER+':' + SECRET +'@mflix.beal2.mongodb.net/test?authSource=admin&replicaSet=atlas-a7tqy4-shard-0&readPreference=primary&appname=MongoDB%20Compass&ssl=true')
    result = client['sample_restaurants']['restaurants'].aggregate([
    {
        '$geoNear': {
            'near': {
                'type': 'Point', 
                'coordinates': coord
            }, 
            'distanceField': 'dist', 
            'maxDistance': distance,
            'key': 'geometry.coordinates', 
            'spherical': True
        }
    }, {
        '$facet': {
            'summary': [
                {
                    '$group': {
                        '_id': '$cuisine', 
                        'closest': {
                            '$min': {
                                '$round': '$dist'
                            }
                        }, 
                        'count': {
                            '$sum': 1
                        }, 
                        'farthest': {
                            '$max': {
                                '$round': '$dist'
                            }
                        }
                    }
                }
            ], 
            'listings': [
                {
                    '$project': {
                        'name': 1, 
                        'long': {
                            '$arrayElemAt': [
                                '$address.coord', 0
                            ]
                        }, 
                        'lat': {
                            '$arrayElemAt': [
                                '$address.coord', 1
                            ]
                        }, 
                        'address': {
                            '$concat': [
                                '$address.building', '  ', '$address.street'
                            ]
                        }, 
                        'cuisine': 1, 
                        'last_grade': {
                            '$arrayElemAt': [
                                '$grades', 0
                            ]
                        }, 
                        'distance': {
                            '$round': '$dist.calculated'
                        }
                    }
                }
            ]
        }
    }
])

    #   panadas can create a DataFrame from the result, but in this case
    #   there are a  couple of manipulations before it is ready to pass onto R
    df = pd.DataFrame(result)

    # create two new DataFrame from both the summary and listing
    summary = df.pop('summary')
    df2 = pd.DataFrame(summary.T[0])

    listings = df.pop('listings')
    df3 = pd.DataFrame(listings.T[0])

    return [df2, df3]