How can I calculate the conditional entropy and find the best information gain from a dataset like this?
The code for calculating entropy:
def entropy(column):
""" Calculates the entropy"""
values, counts = np.unique(column, return_counts=True)
entropy_val = 0
for i in range(len(counts)):
entropy_val += (
(-counts[i] / sum(counts)) * math.log2(counts[i] / (sum(counts)))
)
return entropy_val
where 'column' is a feature in the dataframe, for example df[0]. I'm a little stuck as to where to go from here... Can anyone point me in the right direction, where my end goal is finding best information gain.
entropy_vals = {}
entropy_vals = entropy(X[0]), entropy(X[1]), entropy(X[2]), entropy(X[3]), entropy(y)
print(entropy_vals)
df = pd.read_csv('data_banknote_authentication.txt', header=None)
print(df)
y = df.iloc[:, -1]
X = df.iloc[:, :4]
def count_labels(rows):
"""Counts number of each unique value in selected column."""
counts = {}
for row in rows:
label = row
if label not in counts:
counts[label] = 1
else:
counts[label] += 1
return counts
def entropy(column):
""" Calculates the entropy"""
values, counts = np.unique(column, return_counts=True)
entropy_val = 0
for i in range(len(counts)):
entropy_val += (
(-counts[i] / sum(counts)) * math.log2(counts[i] / (sum(counts)))
)
return entropy_val
entropy_vals = {}
entropy_vals = entropy(X[0]), entropy(X[1]), entropy(X[2]), entropy(X[3]), entropy(y)
print(entropy_vals)
def check_unique(data):
label_col = data[data.columns[-1]]
print(label_col)
unique_features = np.unique(label_col)
if len(unique_features) == 1:
return True
else:
return False
def categorize_data(data):
label_col = data[data.columns[-1]]
values, counts = np.unique(label_col, return_counts=True)
print(values, counts)
index = counts.argmax()
category = values[index]
return category
def split(data):
x_less = data[data <= np.mean(data)]
x_greater = data[data > np.mean(data)]
return x_less, x_greater
