def ANALYSIS_all(division='men', my_data={}, metric=True):
open_data = get_analysis_dataframe(competition='open', division=division)
open_data = clear_outliers(open_data)
regionals_data = get_analysis_dataframe(competition='regionals',
division=division)
regionals_data = clear_outliers(regionals_data)
games_data = get_analysis_dataframe(competition='games', division=division)
games_data = clear_outliers(games_data)
box_plots_all(open_data, regionals_data, games_data, division.title(),
my_data, metric)
def ANALYSIS_all_imputed(division='men', my_data={}, metric=True):
open_data = get_imputed_dataframe(division=division, competition='open')
regionals_data = get_analysis_dataframe(division=division,
competition='regionals')
games_data = get_analysis_dataframe(division=division, competition='games')
# use imputed values from open data to fill in athlete stats for regionals/games data
regionals_data = pd.merge(
open_data.drop(['overallrank', 'overallscore'], axis=1),
regionals_data[['userid', 'overallrank', 'overallscore']],
on='userid',
how='inner')
games_data = pd.merge(open_data.drop(['overallrank', 'overallscore'],
axis=1),
games_data[['userid', 'overallrank',
'overallscore']],
on='userid',
how='inner')
box_plots_all(open_data, regionals_data, games_data,
"Imputed " + division.title(), my_data, metric)
def ANALYSIS_games(division='men'):
games_data = get_analysis_dataframe(competition='games', division=division)
games_data = clear_outliers(games_data)
box_plots(games_data, 'Games')
def ANALYSIS_regionals(division='men'):
regionals_data = get_analysis_dataframe(competition='regionals',
division=division)
regionals_data = clear_outliers(regionals_data)
box_plots(regionals_data, 'Regionals')
def ANALYSIS_open(division='men'):
open_data = get_analysis_dataframe(competition='open', division=division)
open_data = clear_outliers(open_data)
box_plots(open_data, 'Open')
def _get_imputed_dataframe(*args, **kwargs):
def impute_rows(data, X_cols, y_cols):
rows_idx = np.argwhere(
np.logical_and(
np.isnan(data[:, y_cols]).all(axis=1),
~np.isnan(data[:, X_cols]).any(axis=1)))
y_pred = np.zeros((len(rows_idx), len(y_cols)))
if len(rows_idx) > 0:
print("\tImputing", len(rows_idx), "rows")
full_rows = np.argwhere(
np.logical_and(~np.isnan(data[:, X_cols]).any(axis=1),
~np.isnan(data[:, y_cols]).any(axis=1)))
reg = RANSACRegressor()
reg.fit(data[full_rows, X_cols], data[full_rows, y_cols])
y_pred = reg.predict(data[rows_idx, X_cols]).clip(min=0)
return (rows_idx, y_cols, y_pred)
def impute_update_data(data, X_cols, y_cols):
print(X_cols, "predicting", y_cols)
cols = list(data)
X_cols = [cols.index(x) for x in X_cols]
y_cols = [cols.index(y) for y in y_cols]
matrix = data.as_matrix()
rows_idx, y_cols, y_pred = impute_rows(matrix, X_cols, y_cols)
matrix[rows_idx, y_cols] = y_pred
return pd.DataFrame(matrix, index=data.index, columns=data.columns)
data = get_analysis_dataframe(*args, **kwargs)
data = data.astype(float)
data = clear_outliers(data)
Xys = [
#(['Height'],['Weight']),
#(['Weight'],['Height']),
(['Snatch'], ['Clean and Jerk']),
(['Clean and Jerk'], ['Snatch']),
(['Snatch', 'Clean and Jerk'], ['Back Squat']),
(['Snatch', 'Clean and Jerk', 'Back Squat'], ['Deadlift']),
(['Back Squat'], ['Deadlift']),
(['Deadlift'], ['Back Squat']),
#(['Run 5k'],['Sprint 400m']),
#(['Sprint 400m'],['Run 5k']),
(['Weight', 'Snatch', 'Clean and Jerk', 'Back Squat',
'Deadlift'], ['Max Pull-ups']),
(['Weight', 'Back Squat', 'Deadlift'], ['Max Pull-ups']),
(['Weight', 'Snatch', 'Clean and Jerk'], ['Max Pull-ups']),
#(['Filthy 50'],['Fight Gone Bad']),
#(['Fight Gone Bad'],['Filthy 50']),
(['Max Pull-ups', 'Clean and Jerk'], ['Fran']),
(['Clean and Jerk', 'Fran'], ['Grace']),
(['Max Pull-ups', 'Sprint 400m', 'Run 5k'], ['Helen']),
#(['Max Pull-ups', 'Grace'],['Fran']),
]
for x, y in Xys:
data = impute_update_data(data, x, y)
data = clear_outliers(data)
imputer = RecursiveKNN(verbose=1,
n_jobs=4,
feature_selector=DecisionTreeRegressor)
data = pd.DataFrame(imputer.complete(data),
index=data.index,
columns=data.columns)
return data
'Max Pull-ups': 25,
'Fran': 5
}
pan = {
'Age': 22,
'Height': 158,
'Weight': 53,
'Back Squat': 57,
'Clean and Jerk': 35,
'Snatch': 28,
'Deadlift': 70,
'Max Pull-ups': 0
}
fraser = get_analysis_dataframe(division='men',
competition='games').iloc[0].dropna().drop(
['overallscore', 'userid',
'overallrank']).to_dict()
tct = get_analysis_dataframe(division='women',
competition='games').iloc[0].dropna().drop(
['overallscore', 'userid',
'overallrank']).to_dict()
sara = get_analysis_dataframe(division='women',
competition='open').iloc[0].dropna().drop(
['overallscore', 'userid',
'overallrank']).to_dict()
import xgboost as xgb
@memoize()
def get_fitted_model(data):