ollawone

#Load the library and make a basic map
library(leaflet)
leaflet() %>% addTiles()


#Show a map with a satellite picture on it 
leaflet() %>% 
  addTiles(urlTemplate="http://server.arcgisonline.com/ArcGIS/rest/services/World_Imagery/MapServer/tile/{z}/{y}/{x}")

#Make a demo fake data set

ollawone

def filter_graph(pairs, node):
    k_graph = nx.from_pandas_edgelist(pairs, 'subject', 'object',
            create_using=nx.MultiDiGraph())
    edges = nx.dfs_successors(k_graph, node)
    nodes = []
    for k, v in edges.items():
        nodes.extend([k])
        nodes.extend(v)
    subgraph = k_graph.subgraph(nodes)
    layout = (nx.random_layout(k_graph))

ollawone

import networkx as nx
import matplotlib.pyplot as plt


def draw_kg(pairs):
    k_graph = nx.from_pandas_edgelist(pairs, 'subject', 'object',
            create_using=nx.MultiDiGraph())
    node_deg = nx.degree(k_graph)
    layout = nx.spring_layout(k_graph, k=0.15, iterations=20)
    plt.figure(num=None, figsize=(120, 90), dpi=80)

ollawone

import wikipediaapi  # pip install wikipedia-api
import pandas as pd
import concurrent.futures
from tqdm import tqdm

def wiki_scrape(topic_name, verbose=True):
    def wiki_link(link):
        try:
            page = wiki_api.page(link)
            if page.exists():

ollawone

import pandas as pd
import re
import spacy
import neuralcoref

nlp = spacy.load('en_core_web_lg')
neuralcoref.add_to_pipe(nlp)


def entity_pairs(text, coref=True):

ollawone

import wikipediaapi
import pandas as pd

def wiki_page(page_name):
    wiki_api = wikipediaapi.Wikipedia(language='en',
                                      extract_format=wikipediaapi.ExtractFormat.WIKI)
    page_name = wiki_api.page(page_name)
    if not page_name.exists():
        print('page does not exist')
        return

ollawone

# put all selection together
feature_selection_df = pd.DataFrame({'Feature':feature_name, 'Pearson':cor_support, 'Chi-2':chi_support, 'RFE':rfe_support, 'Logistics':embeded_lr_support,
                                    'Random Forest':embeded_rf_support, 'LightGBM':embeded_lgb_support})
# count the selected times for each feature
feature_selection_df['Total'] = np.sum(feature_selection_df, axis=1)
# display the top 100
feature_selection_df = feature_selection_df.sort_values(['Total','Feature'] , ascending=False)
feature_selection_df.index = range(1, len(feature_selection_df)+1)
feature_selection_df.head(num_feats)