if len(sys.argv) < 2:
cmd = input("command please?")
else:
cmd = sys.argv[1]
if cmd.startswith('g'):
do_test = False
else:
do_test = True
force_balanced_classes = True
do_scaling = True
optimise_predictors = True
n_classes = 2
print("n_users",n_users)
cats, cat_lookup, all_qids, users, _stretches_, levels, cat_ixs = init_objects(n_users, seed=666)
#users = open("../mcmc/mcmc_uesrs.txt").read().splitlines()
passdiffs, stretches, passquals, all_qids = load_new_diffs()
mcmcdiffs = load_mcmc_diffs()
reports =[]
report_name = "report_DW{}_{}_fb{}_opt{}_scale{}_{}.txt".format(0, n_users, str(1 if force_balanced_classes else 0), ("001" if optimise_predictors else "0"), ("1" if do_scaling else "0"), featureset_to_use)
if do_test:
report = open(report_name,"w")
for w in [DW_NO_WEIGHT, DW_NATTS, DW_LEVEL, DW_PASSRATE, DW_MCMC, DW_STRETCH]:
for alpha in [1.0, 0.9, 0.6, 0.3, 0.1]:
for phi_retain in [1.0, 0.75, 0.25, 0.0]:
print(cat_ixs)
if do_test:
print(user_summary_df.dtypes)
user_summary_df.iloc[:, 0:15].hist(bins="auto")
plt.show()
exit()
if cmd.startswith('g'):
do_test = False
else:
do_test = True
force_balanced_classes = True
do_scaling = True
optimise_predictors = True
n_classes = 2
print("n_users", n_users)
cats, cat_lookup, all_qids, users, _stretches_, levels, cat_ixs = init_objects(
n_users, path="../../../isaac_data_files/", seed=666)
#users = open("../mcmc/mcmc_uesrs.txt").read().splitlines()
passdiffs, stretches, passquals, all_qids = load_new_diffs(
"../../../isaac_data_files/pass_diffs.csv")
mcmcdf = pd.DataFrame.from_csv(
"../../../isaac_data_files/mcmc/dir_mcmc_results.csv")
sprofs = pd.DataFrame.from_csv(
"../../../isaac_data_files/student_profiling/users_all.csv")
sprofs = sprofs[sprofs["role"] == "STUDENT"]
sprofs = sprofs[sprofs["date_of_birth"].notna()]
sprofs = sprofs[sprofs.index.isin(users)]
users = sprofs.index
print(len(users))
from sklearn.externals import joblib
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, MultiLabelBinarizer
from backfit.BackfitUtils import init_objects
from hwgen.concept_extract import concept_extract, page_to_concept_map
from hwgen.profiler import profile_student
from utils.utils import jaccard_score
base = "../../../isaac_data_files/"
#need to build a softmax classifier to recommend questions...
#this would have qn output nodes
n_users = -1
cats, cat_lookup, _, users, diffs, levels, cat_ixs = init_objects(n_users)
def make_gb_question_map():
gbd_df = pandas.read_csv(base + "gameboards.txt", sep="~")
map = {}
for gb_id, item in zip(gbd_df["id"], gbd_df["questions"]):
if str is not type(item):
continue
# print(gb_id)
# print(item)
item = item[1:-1]
item = item.split(",")
map[gb_id] = item
return map
import random
from matplotlib import pyplot as plt
# INGREDIENTS
# Simulated student
# RL Tutor
# Goal - first to 100 correct questions
from isaac.itemencoding import create_S
target = 1000
n_users = 1000
# random.seed(666)
scores = []
cats, cat_lookup, all_qids, users, diffs, levels, cat_ixs = init_objects(
n_users, path="../../isaacdata/")
passrates, stretches, passquals, all_qids = load_new_diffs(
"../../isaacdata/pass_diffs.csv")
mcmcdf = pandas.read_csv("../../isaacdata/mcmc/dir_mcmc_results.csv",
header=0,
index_col=0)
qtypes = pandas.read_csv("../../isaacdata/atypes.csv",
header=None,
index_col=0)
predictor = pickle.load(open("p_LSVC_0.2_0.5.pkl", "rb"))
scaler = pickle.load(open("qutor_scaler.pkl", "rb"))
print("loaded data")
all_qids = list(all_qids)
random.shuffle(all_qids)
zrows = numpy.nonzero(arr.sum(axis=1)==0)
zcols = numpy.nonzero(arr.sum(axis=0)==0)
arr = numpy.delete(arr, zrows, axis=0)
arr = numpy.delete(arr, zcols, axis=1)
return arr
create_xm = False
plot = True
if __name__ == '__main__':
base = "../../../isaac_data_files/"
#build user experience matrix here....
qmeta = pandas.read_csv(base+"qmeta.csv", header=None)
n_users=1000
cats, cat_lookup, all_qids, users, diffs, levels, cat_ixs = init_objects(n_users, path=base)
levels = set()
lev_lookup = {}
if create_xm:
exp_mx = numpy.zeros(shape = (len(users), len(all_qids)))
print("Created exp_mx of shape:", exp_mx.shape)
for uix,u in enumerate(users):
X = numpy.zeros(shape=(1,len(all_qids)))
uqatts = pandas.read_csv(base+"by_user/{}.txt".format(u), header=None)
runs = extract_runs_w_timestamp(uqatts)
for run in runs:
ts,q,n_atts,n_pass = run
