[Python] Can we write Python code in any other language? [closed]

import pandas as pd
from scipy.stats import chi2_contingency

data = {
'Outlook': ['Sunny', 'Sunny', 'Overcast', 'Rain', 'Rain', 'Rain', 'Overcast', 'Sunny', 'Sunny', 'Rain', 'Sunny',
'Overcast', 'Overcast', 'Rain'],
'Temp.': ['Hot', 'Hot', 'Hot', 'Mild', 'Cool', 'Cool', 'Cool', 'Mild', 'Cold', 'Mild', 'Mild', 'Mild', 'Hot', 'Mild'],
'Humidity': ['High', 'High', 'High', 'High', 'Normal', 'Normal', 'Normal', 'High', 'Normal', 'Normal',
'Normal', 'High', 'Normal', 'High'],
'Wind': ['Weak', 'Strong', 'Weak', 'Weak', 'Weak', 'Strong', 'Strong', 'Weak', 'Weak', 'Weak',
'Strong', 'Strong', 'Weak', 'Strong'],
'Target': ['No', 'No', 'Yes', 'Yes', 'Yes', 'No', 'Yes', 'No', 'Yes', 'Yes', 'Yes', 'Yes', 'Yes', 'No']
}

df = pd.DataFrame(data)

def chaid_split(df, target_col, feature_col):
contingency_table = pd.crosstab(df[feature_col], df[target_col])
chi2, p, dof, expected = chi2_contingency(contingency_table, correction=False)
target_distribution = contingency_table.sum(axis=1) / contingency_table.sum().sum()
return chi2, p, target_distribution.to_dict()

node_counter = 0 # Initialize node counter

def build_chaid_tree(df, target_col, features, forced_root_attributes, min_samples_split=5):
global node_counter
node_counter += 1 # Increment counter for each new node
node_id = node_counter

unique_targets = df[target_col].unique()
if len(unique_targets) <= 1 or len(df) < min_samples_split:
target_counts = df[target_col].value_counts()
target_distribution = target_counts / target_counts.sum()
return {'node_id': node_id, 'label': df[target_col].mode()[0], 'target_distribution': target_distribution.to_dict()}

if forced_root_attributes:
root_attribute = forced_root_attributes.pop(0)
node = {'node_id': node_id, 'attribute': root_attribute, 'children': {}}
for value in df[root_attribute].unique():
subset = df[df[root_attribute] == value]
node['children'][value] = build_chaid_tree(subset, target_col, features, forced_root_attributes.copy(),
min_samples_split)
return node

best_feature = None
best_p_value = 1.0
best_chi2 = None
best_target_distribution = None

for feature in features:
chi2, p, target_distribution = chaid_split(df, target_col, feature)
if p < best_p_value:
best_p_value = p
best_feature = feature
best_chi2 = chi2
best_target_distribution = target_distribution

if best_feature is None:
target_counts = df[target_col].value_counts()
target_distribution = target_counts / target_counts.sum()
return {'node_id': node_id, 'label': df[target_col].mode()[0], 'target_distribution': target_distribution.to_dict()}

node = {'node_id': node_id, 'attribute': best_feature, 'chi2': best_chi2, 'p_value': best_p_value,
'target_distribution': best_target_distribution, 'children': {}}
for value in df[best_feature].unique():
subset = df[df[best_feature] == value]
child_node = build_chaid_tree(subset, target_col, features, [], min_samples_split)
if 'chi2' not in child_node:
child_node['chi2'] = None
child_node['p_value'] = None
child_node['target_distribution'] = child_node['target_distribution']
node['children'][value] = child_node
return node


def print_tree(tree, indent=""):
print(f"Node {tree['node_id']}:") # Added node ID printing
if 'label' in tree:
print(f"{indent}Label: {tree['label']}")
target_distribution = tree.get('target_distribution', {})
total_instances = sum(target_distribution.values())
for target, count in target_distribution.items():
percentage = (count / total_instances) * 100 if total_instances > 0 else 0
print(f"{indent} {target}: ({percentage:.2f}%)")
else:
print(f"{indent}Attribute: {tree['attribute']}")
if 'chi2' in tree:
print(f"{indent}Chi-Square: {tree['chi2']:.3f}")
print(f"{indent}P-Value: {tree['p_value']:.3f}")
target_distribution = tree.get('target_distribution', {})
total_instances = sum(target_distribution.values())
print(f"{indent}Target Distribution:")
for target, count in target_distribution.items():
percentage = (count / total_instances) * 100 if total_instances > 0 else 0
print(f"{indent} {target}: ({percentage:.2f}%)")
for value, child in tree['children'].items():
print_tree(child, indent + " ")


tree = build_chaid_tree(df, 'Target', ['Outlook', 'Temp.', 'Humidity', 'Wind'], ['Outlook',"Wind","Humidity"], min_samples_split=3)
print_tree(tree)


Not tried anything yet

Continue reading...