graph_elements = { "Apple" : ["Banana","Cherry"],
                "Banana" : ["Apple", "Durian"],
                "Cherry" : ["Apple", "Durian"],
                "Durian" : ["Orange"],
                "Orange" : ["Durian"]
                }

class graph:

    def __init__(self, value=None):
      self.value = value

    def getVertices(self):
      return list(self.value.keys())

    def getEdges(self):
      return self.edges()

    def edges(self):
        edgelist = []
        for vertex in self.value:
            for neighbor in self.value[vertex]:
                if {neighbor, vertex} not in edgelist:
                    edgelist.append({vertex, neighbor})
        return edgelist

g = graph(graph_elements)


print(g.getVertices())
print(g.getEdges())

def depth_first_search(graph, start, visited=None):
  if visited is None:
    visited = set()
  visited.add(start)

  #print(start)

  for next in graph[start] - visited:
    depth_first_search(graph, next, visited)
  return visited

graph = {'Apple': set(['Banana', 'Cherry']),
         'Banana': set(['Apple', 'Durian', 'Orange']),
         'Cherry': set(['Apple']),
         'Durian': set(['Banana', 'Orange']),
         'Orange': set(['Cherry', 'Durian'])
         }


depth_first_search(graph, 'Banana')

import collections

def breadth_first_search(graph, root):

    visited, queue = set(), collections.deque([root])
    visited.add(root)

    while queue:

        vertex = queue.popleft()
        print(str(vertex) + " ", end="")

        for neighbour in graph[vertex]:
            if neighbour not in visited:
                visited.add(neighbour)
                queue.append(neighbour)


if __name__ == '__main__':

    graph = {0: [1, 2], 
             1: [0, 2], 
             2: [3], 
             3: [1, 2]
             }


breadth_first_search(graph, 1)

from google.colab import drive
drive.mount('/data/')
data_dir = '/data/My Drive/Colab Notebooks/FEC dataset'
!ls '/data/My Drive/Colab Notebooks/FEC dataset'

from zipfile import ZipFile

header = pd.read_csv(data_dir+'/cn_header_file.csv')

with ZipFile(data_dir+'/cn20.zip') as zip:
  candidates = pd.read_csv(zip.open('cn.txt'), sep='|', names=header.columns)
candidates.head()

candidates[candidates['CAND_NAME'].str.contains('WALKER')].head()

tg = candidates[(candidates['CAND_ELECTION_YR'] == 2020) & (candidates['CAND_OFFICE_ST'] == 'FL')]
tg.head()

len(tg.index)

candidates[candidates['CAND_NAME'].str.contains('TRUMP, DONALD')]

header = pd.read_csv(data_dir+'/pas2_header_file.csv')

with ZipFile(data_dir+'/pas220.zip') as zip:
  #print(zip.namelist())
  spending = pd.read_csv(zip.open('itpas2.txt'), sep='|', names=header.columns)
spending.head()

house_spending_FL = spending[(spending['CAND_ID'].str.startswith('H')==True) & (spending['STATE']=='FL')]
df_house = house_spending_FL[['CMTE_ID', 'NAME', 'STATE', 'TRANSACTION_AMT', 'CAND_ID']]
df_house.head()

header = pd.read_csv(data_dir+'/cm_header_file.csv')

with ZipFile(data_dir+'/cm20.zip') as zip:
  #print(zip.namelist())
  df = pd.read_csv(zip.open('cm.txt'), sep='|', names=header.columns)
df.head()

df_name = df[['CMTE_ID', 'CMTE_NM']]
df_name.head()

Society_Organization = df[df['CONNECTED_ORG_NM'].str.contains('SOCIETY', na=False)]
Society_Organization.head()

len(Society_Organization.index)

header = pd.read_csv(data_dir+'/ccl_header_file.csv')

with ZipFile(data_dir+'/ccl20.zip') as zip:
  #print(zip.namelist())
  linkage = pd.read_csv(zip.open('ccl.txt'), sep='|', names=header.columns)

linkage.head()

df1.head()

df2 = pd.merge(candidates, linkage, on='CAND_ID')
df2.head()

df_sort[df_sort['CAND_ST']=='FL'].head(10)

df_sort_house = pd.merge(df_sort, df_house, on='CAND_ID')
df_sort_house.head()

df_sort_house['TRANSACTION_AMT'].sum()