Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

a little cleanup #1

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

a little cleanup #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions adult.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,6 @@ def run_a_experiments():
acc, std, time, sparsity, dimensions = cv_binary_classification(model, X, y, continuous, categorical, encoder=BetaEncoder(alpha=alpha_prior, beta=1-alpha_prior), moments='mv')
results.append([type(model), 'BetaEncoder (mv)', acc, std, time, sparsity, dimensions])


file = 'adult_experiments.csv'
with open(file, "w") as output:
writer = csv.writer(output, lineterminator='\n')
Expand All @@ -88,8 +87,10 @@ def run_a_experiments():
except:
print("File Not Uploaded")

def load_data(local=False):
if not local:

def load_data():
exists = os.path.isfile('adult_raw.csv')
if not exists:
url="https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data"
r=requests.get(url).content
df=pd.read_csv(io.StringIO(r.decode('utf-8')),header=None)
Expand All @@ -113,13 +114,13 @@ def load_data(local=False):
'hours-per-week',
'native-country',
'class']
new_name = dict(enumerate(names))

new_name = {str(k): v for k, v in dict(enumerate(names)).items()}
df = df.rename(new_name,axis='columns')
df['class'] = (df['class']==' >50K').astype(int)

return df


if __name__ == '__main__':
run_a_experiments()