def fnopt(par):
loss = log_loss(trainreal, logitinv(par[0] * trainpred + par[1]))
return loss
def fnopt(par):
loss = log_loss(trainreal, logitinv(par[0]*trainpred+par[1]))
return loss
# optimize probability
optpar = np.array([0.0, 0.0])
for grade, col in enumerate(scores):
trainpred = np.array(preds.ix[preds.essay_type == "TRAINING", col])
trainreal = np.array(
(realscores[preds.essay_type == "TRAINING"] == grade).map(int))
def fnopt(par):
loss = log_loss(trainreal, logitinv(par[0] * trainpred + par[1]))
return loss
opt = fmin(fnopt, np.array([0.0, 0.0]))
optpar += opt
optpar /= len(scores)
preds.ix[:, scores] = logitinv(optpar[0] * preds.ix[:, scores] + optpar[1])
preds_validation = preds.ix[preds.essay_type == "VALIDATION", :]
assert np.all(
np.argmax(preds_validation.ix[:, scores].as_matrix(), axis=1) ==
np.array(preds_validation.final_score))
items = []
for _, record in preds_validation.iterrows():
record = dict(record)
record["item_id"] = item_id
item = ITEM_XML % dict(record)
items.append(item)
preds_validation.ix[:, ["student_id", "test_id", "final_score"] +
scores].to_csv("final_scores/" + item_id +
realscores = essays.meta_data()["score3"]
scores = [col for col in preds.columns if col.find("prob") > 0]
# optimize probability
optpar = np.array([0.0,0.0])
for grade,col in enumerate(scores):
trainpred = np.array(preds.ix[preds.essay_type=="TRAINING",col])
trainreal = np.array((realscores[preds.essay_type=="TRAINING"]==grade).map(int))
def fnopt(par):
loss = log_loss(trainreal, logitinv(par[0]*trainpred+par[1]))
return loss
opt = fmin(fnopt, np.array([0.0,0.0]))
optpar += opt
optpar /= len(scores)
preds.ix[:,scores] = logitinv(optpar[0]*preds.ix[:,scores]+optpar[1])
preds_validation = preds.ix[preds.essay_type=="VALIDATION",:]
assert np.all(np.argmax(preds_validation.ix[:,scores].as_matrix(),axis=1)==np.array(preds_validation.final_score))
items = []
for _, record in preds_validation.iterrows():
record = dict(record)
record["item_id"] = item_id
item = ITEM_XML % dict(record)
items.append(item)
preds_validation.ix[:,["student_id","test_id","final_score"] + scores].to_csv("final_scores/" + item_id + "_AI-PJ_scores_probs.csv",index=False)
out = open("final_scores/" + item_id + "_AI-PJ_scores.xml","w")
out.write(ALL_XML % ("".join(items)))
out.close()
