raghavrv

raghavrv

raghavrv

# Generating the sample data from make_blobs

X, y = make_blobs(n_samples=100,
                  n_features=2,
                  centers=4,
                  cluster_std=1.0,
                  center_box=(-10.0, 10.0),
                  shuffle=True,
                  random_state=0) # For reproducibility

raghavrv

%matplotlib inline
import matplotlib.pyplot as plt
from matplotlib.patches import Arc

from math import sqrt

fig = plt.figure()
ax = fig.add_subplot(111)

fig.set_size_inches(10, 5)

raghavrv

import requests
import bs4

def get_codechef_userstats(user_id):
    soup = bs4.BeautifulSoup(
    requests.get('https://www.codechef.com/users/%s' % user_id).content)
    # Parse the data in the first td tag of the 2nd tr tag of the table with id "problem_stats"
    stats_row = soup.find('table', {'id': 'problem_stats'}).findAll('tr')[1].findAll('td')
    n_solved = int(stats_row[0].text)
    n_submitted = int(stats_row[2].text)

raghavrv

*swp
*ipynb_checkpoints
*build
*.dat

raghavrv

from IPython.display import Markdown, HTML, display_markdown
from glob import glob

cpp_markdown_template = """```cpp\n%s\n```\n<hr>"""

for i, problem in enumerate(
        glob("/media/rvraghav93/code/projects/competitive_programming/codechef/*.cpp")):  
    with open(problem) as f:
        code = f.read().splitlines()
        url = code[0]

raghavrv

# Load categories of categorical features from descr


descr = """@attribute Age real [17.0, 90.0]
@attribute Workclass {Private, Self-emp-not-inc, Self-emp-inc, Federal-gov, Local-gov, State-gov, Without-pay, Never-worked}
@attribute Fnlwgt real [12285.0, 1490400.0]
@attribute Education {Bachelors, Some-college, 11th, HS-grad, Prof-school, Assoc-acdm, Assoc-voc, 9th, 7th-8th, 12th, Masters, 1st-4th, 10th, Doctorate, 5th-6th, Preschool}
@attribute Education-num real [1.0, 16.0]
@attribute Marital-status {Married-civ-spouse, Divorced, Never-married, Separated, Widowed, Married-spouse-absent, Married-AF-spouse}
@attribute Occupation {Tech-support, Craft-repair, Other-service, Sales, Exec-managerial, Prof-specialty, Handlers-cleaners, Machine-op-inspct, Adm-clerical, Farming-fishing, Transport-moving, Priv-house-serv, Protective-serv, Armed-Forces}

raghavrv

# The census income dataset with 0.2 million datapoints
# http://sci2s.ugr.es/keel/dataset.php?cod=195

# Load categories of categorical features from descr

descr = """@attribute Atr-0 integer[0,90]
@attribute Atr-1 {Self-employed-not_incorporated,Not_in_universe,Private,Local_government,Federal_government,Self-employed-incorporated,State_government,Never_worked,Without_pay}
@attribute Atr-2 integer[0,51]
@attribute Atr-3 integer[0,46]
@attribute Atr-4 {Some_college_but_no_degree,10th_grade,Children,Bachelors_degree(BA_AB_BS),High_school_graduate,Masters_degree(MA_MS_MEng_MEd_MSW_MBA),Less_than_1st_grade,Associates_degree-academic_program,7th_and_8th_grade,12th_grade_no_diploma,Associates_degree-occup_/vocational,Prof_school_degree_(MD_DDS_DVM_LLB_JD),5th_or_6th_grade,11th_grade,Doctorate_degree(PhD_EdD),9th_grade,1st_2nd_3rd_or_4th_grade}

raghavrv

from sklearn.utils import check_X_y, check_random_state
import numpy as np

def drop_values(X, y=None, missing_mask=None,
                missing_values="NaN",
                missing_fraction=0.1,
                label_correlation=1.0,
                n_labels=1,
                labels=None,
                missing_mask_only=False,