I have some machine learning results that I am trying to make sense of. The task is to predict/label "Irish" vs. "non-Irish". Python 2.7's output:
1= ir
0= non-ir
Class count:
0 4090942
1 940852
Name: ethnicity_scan, dtype: int64
Accuracy: 0.874921350119
Classification report:
precision recall f1-score support
0 0.89 0.96 0.93 2045610
1 0.74 0.51 0.60 470287
avg / total 0.87 0.87 0.87 2515897
Confusion matrix:
[[1961422 84188]
[ 230497 239790]]
AUC-ir= 0.901238104773
As you can see, the precision and recall are mediocre, but the AUC-ROC is higher (~0.90). And I am trying to figure out why, which I suspect is due to data imbalance (about 1:5). Based on the confusion matrix, and using Irish as the target (+), I calculated the TPR=0.51 and FPR=0.04. If I am considering non-Irish as (+), then TPR=0.96 and FPR=0.49. So how can I get a 0.9 AUC while the TPR can be only 0.5 at FPR=0.04?
Codes:
try:
for i in mass[k]:
df = df_temp # reset df before each loop
#$$
#$$
if 1==1:
###if i == singleEthnic:
count+=1
ethnicity_tar = str(i) # fr, en, ir, sc, others, ab, rus, ch, it, jp
# fn, metis, inuit; algonquian, iroquoian, athapaskan, wakashan, siouan, salish, tsimshian, kootenay
############################################
############################################
def ethnicity_target(row):
try:
if row[ethnicity_var] == ethnicity_tar:
return 1
else:
return 0
except: return None
df['ethnicity_scan'] = df.apply(ethnicity_target, axis=1)
print '1=', ethnicity_tar
print '0=', 'non-'+ethnicity_tar
# Random sampling a smaller dataframe for debugging
rows = df.sample(n=subsample_size, random_state=seed) # Seed gives fixed randomness
df = DataFrame(rows)
print 'Class count:'
print df['ethnicity_scan'].value_counts()
# Assign X and y variables
X = df.raw_name.values
X2 = df.name.values
X3 = df.gender.values
X4 = df.location.values
y = df.ethnicity_scan.values
# Feature extraction functions
def feature_full_name(nameString):
try:
full_name = nameString
if len(full_name) > 1: # not accept name with only 1 character
return full_name
else: return '?'
except: return '?'
def feature_full_last_name(nameString):
try:
last_name = nameString.rsplit(None, 1)[-1]
if len(last_name) > 1: # not accept name with only 1 character
return last_name
else: return '?'
except: return '?'
def feature_full_first_name(nameString):
try:
first_name = nameString.rsplit(' ', 1)[0]
if len(first_name) > 1: # not accept name with only 1 character
return first_name
else: return '?'
except: return '?'
# Transform format of X variables, and spit out a numpy array for all features
my_dict = [{'last-name': feature_full_last_name(i)} for i in X]
my_dict5 = [{'first-name': feature_full_first_name(i)} for i in X]
all_dict = []
for i in range(0, len(my_dict)):
temp_dict = dict(
my_dict[i].items() + my_dict5[i].items()
)
all_dict.append(temp_dict)
newX = dv.fit_transform(all_dict)
# Separate the training and testing data sets
X_train, X_test, y_train, y_test = cross_validation.train_test_split(newX, y, test_size=testTrainSplit)
# Fitting X and y into model, using training data
classifierUsed2.fit(X_train, y_train)
# Making predictions using trained data
y_train_predictions = classifierUsed2.predict(X_train)
y_test_predictions = classifierUsed2.predict(X_test)
Inserted codes for resampling:
try:
for i in mass[k]:
df = df_temp # reset df before each loop
#$$
#$$
if 1==1:
###if i == singleEthnic:
count+=1
ethnicity_tar = str(i) # fr, en, ir, sc, others, ab, rus, ch, it, jp
# fn, metis, inuit; algonquian, iroquoian, athapaskan, wakashan, siouan, salish, tsimshian, kootenay
############################################
############################################
def ethnicity_target(row):
try:
if row[ethnicity_var] == ethnicity_tar:
return 1
else:
return 0
except: return None
df['ethnicity_scan'] = df.apply(ethnicity_target, axis=1)
print '1=', ethnicity_tar
print '0=', 'non-'+ethnicity_tar
# Resampled
df_resampled = df.append(df[df.ethnicity_scan==0].sample(len(df)*5, replace=True))
# Random sampling a smaller dataframe for debugging
rows = df_resampled.sample(n=subsample_size, random_state=seed) # Seed gives fixed randomness
df = DataFrame(rows)
print 'Class count:'
print df['ethnicity_scan'].value_counts()
# Assign X and y variables
X = df.raw_name.values
X2 = df.name.values
X3 = df.gender.values
X4 = df.location.values
y = df.ethnicity_scan.values
# Feature extraction functions
def feature_full_name(nameString):
try:
full_name = nameString
if len(full_name) > 1: # not accept name with only 1 character
return full_name
else: return '?'
except: return '?'
def feature_full_last_name(nameString):
try:
last_name = nameString.rsplit(None, 1)[-1]
if len(last_name) > 1: # not accept name with only 1 character
return last_name
else: return '?'
except: return '?'
def feature_full_first_name(nameString):
try:
first_name = nameString.rsplit(' ', 1)[0]
if len(first_name) > 1: # not accept name with only 1 character
return first_name
else: return '?'
except: return '?'
# Transform format of X variables, and spit out a numpy array for all features
my_dict = [{'last-name': feature_full_last_name(i)} for i in X]
my_dict5 = [{'first-name': feature_full_first_name(i)} for i in X]
all_dict = []
for i in range(0, len(my_dict)):
temp_dict = dict(
my_dict[i].items() + my_dict5[i].items()
)
all_dict.append(temp_dict)
newX = dv.fit_transform(all_dict)
# Separate the training and testing data sets
X_train, X_test, y_train, y_test = cross_validation.train_test_split(newX, y, test_size=testTrainSplit)
# Fitting X and y into model, using training data
classifierUsed2.fit(X_train, y_train)
# Making predictions using trained data
y_train_predictions = classifierUsed2.predict(X_train)
y_test_predictions = classifierUsed2.predict(X_test)
