get_dummies

get_dummies.py

# Initialize the dataframe 'numerical_nucleotide' of shape (106,(57*4))

numerical_nucleotide = pd.DataFrame(np.random.randn(106,(57*4)))

# Define the dictionary 'key1'
key1 = {'a' : '1000','c' : '0100','g' : '0010','t' : '0001'}

# Assign values to 'numerical_nucleotide'

for i in range(nucleotide_sequence.shape[0]):
  temp1 = '' 
  for j in range(nucleotide_sequence.shape[1]-1):
    temp1 = temp1 + key1[nucleotide_sequence[j][i]]
  temp2 = [int(x) for x in list(temp1)]
  numerical_nucleotide.iloc[i] = temp2

# Assign 'Class' column to 'numerical_nucleotide'

numerical_nucleotide['Class'] = nucleotide_sequence['Class']

# Replace '+' and '-' of 'Class' column with values 1 and 0 respectively

numerical_nucleotide.replace(to_replace = '+',value = 1,inplace = True)
numerical_nucleotide.replace(to_replace = '-',value = 0,inplace = True)

print(numerical_nucleotide)