def plot_histogram_with_dummies_theoretical(self): if not self.clustering: raise ValueError('Clustering not performed yet') new_histogram, full_histogram = utils.build_clustered_histograms( self.histogram, self.labels) utils.plot_histograms(original_histogram=new_histogram, theoretical_dummies=full_histogram)
def plot_histogram_with_dummies_real(self): if not self.dummies: raise ValueError('Dummies not generated yet') _, theoretical_dummies = utils.build_clustered_histograms( self.histogram, self.labels) histogram_with_dummies = self.patient_concepts_matrix_dummies.sum(0) cluster_indexing = theoretical_dummies.index utils.plot_histograms(self.histogram[cluster_indexing], theoretical_dummies[cluster_indexing], histogram_with_dummies[cluster_indexing])
# print(data.head()) data = data[data['Year'] < 2002] data['RD'] = data['RS'] - data['RA'] in_playoffs = data[data['Playoffs'] == 1] out_playoffs = data[data['Playoffs'] == 0] from utils import plot_scatters, plot_histograms, plot_deriving_slope plot_scatters(in_playoffs, out_playoffs, label='RS') plot_scatters(in_playoffs, out_playoffs, label='RD', RDxline=False, x=data['RD'].values, y=data['W'].values) plot_histograms(data) # plot_deriving_slope(data['RD'].values, data['W'].values) from matplotlib import pyplot as plt plt.show() rd_to_wins = data[['RD', 'W']].corr() dePodesta = data[['OBP', 'SLG', 'BA', 'RS']].corr() from sklearn.linear_model import LinearRegression modelRS = LinearRegression() modelRS.fit(data[['OBP', 'SLG']].values, data['RS'].values) print(f"bias RS: {modelRS.intercept_}") print(f"Coefficients: {modelRS.coef_}") RA_data = data.dropna()
def plot_histogram(self): utils.plot_histograms(original_histogram=self.histogram)
plt.figure(3) plt.plot(np.arange(T), opt_arms_rate_mean, label=algo) plt.fill_between(time, opt_arms_rate_mean - (q / np.sqrt(n_itr)) * np.sqrt(opt_arms_rate_var), opt_arms_rate_mean + (q / np.sqrt(n_itr)) * np.sqrt(opt_arms_rate_var), color='#D3D3D3') plt.xlabel('Rounds') plt.ylabel('$\%$') plt.title('Rate of optimal arms pulling, averaged over ' + str(n_itr) + ' runs') plt.legend() if plot_histo: fig = plot_histograms(algo, histograms, hist_times, K, A_star) alpha_star, opt_mix_rew = MO_MAB.alpha_star, MO_MAB.optimal_mixed_rew print('Optimal mixed reward = ' + str(opt_mix_rew)) alpha = ogde.alpha.reshape((1, K)) opt_mix = alpha.dot(MO_MAB.O)[0] print('Mixed reward at time T = ' + str(opt_mix)) print('') print('Alpha_star = ' + str(alpha_star)) print('Alpha_T = ' + str(alpha[0])) if plot_arms and D in [2, 3]: plot_momab(MO_MAB, opt_mix, alpha_ogde=alpha_ogde,
print("You didn't specify any plot types, exiting") sys.exit(1) connectstring = dbutils.make_connectstring(db="views", hostname="VIEWSHOST", port="5432", prefix="postgres", uname="VIEWSADMIN") dir_descriptive = "/storage/runs/current/descriptive" dir_table = "/".join([dir_descriptive, schema, table]) df = dbutils.db_to_df(connectstring, schema, table, ids=[timevar, groupvar]) df.sort_index(inplace=True) if plot_wawa: utils.plot_world_average_with_actuals(df, connectstring, dir_table, timevar, groupvar) if plot_spaghetti: utils.plot_spaghetties(df, connectstring, dir_table) if plot_hist: utils.plot_histograms(df, dir_table) if plot_lpg: utils.plot_lines_per_group(df, dir_table) if plot_abt: utils.plot_stats_by_time(df, dir_table) if plot_pgcm: utils.plot_pgcm(df, connectstring, dir_table) if plot_lpgwa: utils.plot_lines_per_group_with_actuals(df, connectstring, dir_table)