champAnalysis.py 文件源码

def get_p_vals(role1,champ1,single_counts=True,span=3):
    # Use a chi-squared test to calculate p-values to compare the recommendation 
    # distributions for the top 3 champs vs the next few recommendations.
    champ1=str(champ2id.get(champ1,champ1))
    p_vals = {}
    for role2 in recs[tier][role1][champ1]:
        p_vals[role2] = {}
        if role2=='TOTAL' or role2=='DATA': 
            continue
        for idx in range(1,4):
            values = []
            for pos_to_compare in range(idx+1,idx+1+span):
                # Get ids from recs:
                champ2_1 = str(champ2id[recs[tier][role1][champ1][role2][idx]['champ']])
                champ2_2 = str(champ2id[recs[tier][role1][champ1][role2][pos_to_compare]['champ']])
                # Get data:
                N = recs[tier][role1][champ1][role2]['N']
                if N > 10:
                    data = sliding_count_recs[tier][role1][champ1][role2]
                    champ2_1_data = np.array(data['DATA'][champ2_1] + [0]*(N-len(data['DATA'][champ2_1])))
                    champ2_2_data = np.array(data['DATA'][champ2_2] + [0]*(N-len(data['DATA'][champ2_2])))
                    if single_counts:
                        champ2_1_data[champ2_1_data>0]=1
                        champ2_2_data[champ2_2_data>0]=1
                    contingency_mat = np.array([[sum(champ2_1_data), N-sum(champ2_1_data)],[sum(champ2_2_data),N-sum(champ2_2_data)]])
                    values.append(chi2_contingency(contingency_mat)[1])
                else:
                    values.append(1)
            p_vals[role2][idx] = values
    return p_vals