!pip install pybbn

import pandas as pd
import networkx as nx
import matplotlib.pyplot as plt
from pybbn.graph.dag import Bbn
from pybbn.graph.edge import Edge, EdgeType
from pybbn.graph.jointree import EvidenceBuilder
from pybbn.graph.node import BbnNode
from pybbn.graph.variable import Variable
from pybbn.pptc.inferencecontroller import InferenceController #Set Pandas options to display more columns
pd.options.display.max_columns=50
df=pd.read_csv('weatherAUS.csv', encoding='utf-8')
df=df[pd.isnull(df['RainTomorrow'])==False]
df=df.fillna(df.mean())
df['WindGustSpeedCat']=df['WindGustSpeed'].apply(lambda x: '0.<=40' if x<=40 else 
                                                   '1.40-50'  if 40<x<=50 else '2.>50')
df['Humidity9amCat' ]=df[ 'Humidity9am'].apply(lambda x: '1.>60' if x>60 else '0.<=60')
df['Humidity3pmCat']=df['Humidity3pm'].apply(lambda x: '1.>60' if x>60 else '0.<=60')
print(df)

def probs(data, child, parent1=None, parent2=None):
  if parent1==None:
    prob=pd.crosstab(data[child],'Empty', margins=False, normalize='columns').sort_index().to_numpy().reshape(-1).tolist()
  elif parent1!=None:
    if parent2==None:
      prob=pd.crosstab(data[parent1],data[child], margins=False, normalize='index').sort_index().to_numpy().reshape(-1).tolist()
    else:
      prob=pd. crosstab([data[parent1], data[parent2]],data[child], margins=False, normalize='index').sort_index().to_numpy().reshape(-1).tolist()
  else: print("Error in Probability Frequency Calculations")
  return prob
H9am = BbnNode(Variable(0, 'H9am', ['<=60', '>60']), probs(df, child='Humidity9amCat'))
H3pm = BbnNode(Variable(1, 'H3pm', ['<=60', '>60']), probs(df, child= 'Humidity3pmCat', parent1='Humidity9amCat'))
W =BbnNode(Variable(2, 'W', ['<=40', '40-50', '>50']), probs(df, child='WindGustSpeedCat'))
RT = BbnNode(Variable(3, 'RT', ['No', 'Yes']), probs(df, child='RainTomorrow', parent1='Humidity3pmCat', parent2='WindGustSpeedCat'))

bbn= Bbn() \
  .add_node(H9am) \
  .add_node(H3pm) \
  .add_node(W) \
  .add_node(RT) \
  .add_edge(Edge(H9am,H3pm, EdgeType.DIRECTED)) \
  .add_edge(Edge(H3pm, RT, EdgeType.DIRECTED)) \
  .add_edge(Edge(W,RT, EdgeType.DIRECTED))

join_tree =InferenceController.apply(bbn)
pos={0: (-1,2), 1: (-1, 0.5), 2: (1, 0.5), 3:(0,-1)}
options ={
"font_size": 16,
"node_size": 4000,
"node_color": "red",
"edgecolors": "blue",
"edge_color": "black",
"linewidths": 5,
"width": 5,
}
n,d=bbn.to_nx_graph()
nx.draw(n, with_labels=True,labels=d, pos=pos, **options)

ax=plt.gca()
ax.margins (0.20)
plt.axis("off")
plt.show()

import networkx as nx
import pandas as pd
import matplotlib.pyplot as plt
from pybbn.graph.dag import Bbn
from pybbn.graph.dag import Edge,EdgeType
from pybbn.graph.jointree import EvidenceBuilder
from pybbn.graph.node import BbnNode
from pybbn.graph.variable import Variable
from pybbn.pptc.inferencecontroller import InferenceController
pd.options.display.max_columns=50
df=pd.read_csv('weatherAUS.csv',encoding='utf-8')
df=df[pd.isnull(df['RainTomorrow'])==False]
# For other columns with missing values, fill them in with column mean
df=df.fillna(df.mean())
# Create bands for variables that we want to use in the model
df['WindGustSpeedCat']=df['WindGustSpeed'].apply(lambda x: '0.<=40'   if x<=40 else
                                                            '1.40-50' if 40<x<=50 else '2.>50')
df['Humidity9amCat']=df['Humidity9am'].apply(lambda x: '1.>60' if x>60 else '0.<=60')
df['Humidity3pmCat']=df['Humidity3pm'].apply(lambda x: '1.>60' if x>60 else '0.<=60')
# Show a snaphsot of data
print(df)
# This function helps to calculate probability distribution, which goes into BBN (note, can handle up to 2 parents)
def probs(data, child, parent1=None, parent2=None):
    if parent1==None:
        # Calculate probabilities
        prob=pd.crosstab(data[child], 'Empty', margins=False, normalize='columns').sort_index().to_numpy().reshape(-1).tolist()
    elif parent1!=None:
            # Check if child node has 1 parent or 2 parents
            if parent2==None:
                # Caclucate probabilities
                prob=pd.crosstab(data[parent1],data[child], margins=False, normalize='index').sort_index().to_numpy().reshape(-1).tolist()
            else:
                # Caclucate probabilities
                prob=pd.crosstab([data[parent1],data[parent2]],data[child], margins=False, normalize='index').sort_index().to_numpy().reshape(-1).tolist()
    else: print("Error in Probability Frequency Calculations")
    return prob
# Create nodes by using our earlier function to automatically calculate probabilities
H9am = BbnNode(Variable(0, 'H9am', ['<=60', '>60']), probs(df, child='Humidity9amCat'))
H3pm = BbnNode(Variable(1, 'H3pm', ['<=60', '>60']), probs(df, child='Humidity3pmCat', parent1='Humidity9amCat'))
W = BbnNode(Variable(2, 'W', ['<=40', '40-50', '>50']), probs(df, child='WindGustSpeedCat'))
RT = BbnNode(Variable(3, 'RT', ['No', 'Yes']), probs(df, child='RainTomorrow', parent1='Humidity3pmCat', parent2='WindGustSpeedCat'))

# Create Network
bbn = Bbn() \
    .add_node(H9am) \
    .add_node(H3pm) \
    .add_node(W) \
    .add_node(RT) \
    .add_edge(Edge(H9am, H3pm, EdgeType.DIRECTED)) \
    .add_edge(Edge(H3pm, RT, EdgeType.DIRECTED)) \
    .add_edge(Edge(W, RT, EdgeType.DIRECTED))

# Convert the BBN to a join tree
join_tree = InferenceController.apply(bbn)
# Set node positions
pos = {0: (-1, -2), 1: (-1, 0.5), 2: (1, 0.5), 3: (0, -1)}

# Set options for graph looks
options = {
    "font_size": 16,
    "node_size": 4000,
    "node_color": "magenta",
    "edgecolors": "black",
    "edge_color": "blue",
    "linewidths": 5,
    "width": 5,}

# Generate graph
n, d = bbn.to_nx_graph()
nx.draw(n, with_labels=True, labels=d, pos=pos, **options)

# Update margins and print the graph
ax = plt.gca()
ax.margins(0.10)
plt.axis("off")
plt.show()