ou are given the following three functions. They take plain text names and covert then into features vefctors so that you can work with them in a classification system.
Hashing Project in Python to Extract Features of Names
You are given the following three functions. They take plain text names and covert then into features vefctors so that you can work with them in a classification system.
Let's check your understanding of Python function. Add notes to each line describing what is happening in these functions.
FUNCTION ONE:
def hashfeatures(baby, B, FIX):
"""
Input:
baby : a string representing the baby's name to be hashed
B: the number of dimensions to be in the feature vector
FIX: the number of chunks to extract and hash from each string
Output:
v: a feature vector representing the input string
"""
v = np.zeros(B)
for m in range(FIX):
featurestring = "prefix" + baby[:m]
v[hash(featurestring) % B] = 1
featurestring = "suffix" + baby[-1*m:]
v[hash(featurestring) % B] = 1
return v
FUNCTION TWO:
def name2features(filename, B=128, FIX=3, LoadFile=True):
"""
Output:
X : n feature
"""
# read in baby names
if LoadFile:
with open(filename, 'r') as f:
babynames = [x.rstrip() for x in f.readlines() if len(x) > 0]
else:
babynames = filename.split('n')
n = len(babynames)
X = np.zeros((n, B))
for i in range(n):
X[i,:] = hashfeatures(babynames[i], B, FIX)
return X
FUNCTION THREE:
def genTrainFeatures(dimension=128):
"""
Input:
dimension: desired dimension of the features
Output:
X: n feature vectors of dimensionality d (nxd)
Y: n labels (-1 = girl, +1 = boy) (n)
"""
# Load in the data
Xgirls = name2features("girls.train", B=dimension)
Xboys = name2features("boys.train", B=dimension)
X = np.concatenate([Xgirls, Xboys])
# Generate Labels
Y = np.concatenate([-np.ones(len(Xgirls)), np.ones(len(Xboys))])
# shuffle data into random order
ii = np.random.permutation([i for i in range(len(Y))])
return X[ii, :], Y[ii]
Trending now
This is a popular solution!
Step by step
Solved in 2 steps
