import sys
sys.path.append('../')
import numpy as np
from pyBKT.models import Model
np.seterr(divide='ignore', invalid='ignore')
skills = ["Percent Of", "Addition and Subtraction Integers", "Conversion of Fraction Decimals Percents", "Volume Rectangular Prism", "Venn Diagram", "Equation Solving Two or Fewer Steps", "Volume Cylinder", "Multiplication and Division Integers", "Area Rectangle", "Addition and Subtraction Fractions", ]
model = Model(seed = 0, num_fits = 1)
print("BKT")
print(model.crossvalidate(data_path = "data/as.csv", skills = skills, metric = "rmse")["rmse"].values)
print()
print("Item Learning Effect")
print(model.crossvalidate(data_path = "data/as.csv", skills = skills, multilearn = "problem_id", metric = "rmse")["rmse"].values)
import numpy as np
from pyBKT.models import Model
np.seterr(divide='ignore', invalid='ignore')
skills = [
"Percent Of",
"Addition and Subtraction Integers",
"Conversion of Fraction Decimals Percents",
"Volume Rectangular Prism",
"Venn Diagram",
"Equation Solving Two or Fewer Steps",
"Volume Cylinder",
"Multiplication and Division Integers",
"Area Rectangle",
"Addition and Subtraction Fractions",
]
model = Model(seed=0, num_fits=20)
print("BKT")
#print(model.crossvalidate(data_path = "data/as.csv", skills = skills, metric = "auc"))
print(
model.crossvalidate(data_path="data/as.csv", skills=skills, metric="rmse"))
print()
print("KT-IDEM")
#print(model.crossvalidate(data_path = "data/as.csv", skills = skills, multigs = True, metric = "auc"))
print(
model.crossvalidate(data_path="data/as.csv",
skills=skills,
multigs=True,
metric="rmse"))
import sys
sys.path.append('../')
import numpy as np
from pyBKT.models import Model
np.seterr(divide='ignore', invalid='ignore')
#only one skill is shown due to the high time complexity needed to fit the item order effect model
skills = ["Venn Diagram"]
model = Model(seed=0, num_fits=10)
print("BKT")
print(
model.crossvalidate(data_path="data/as.csv", skills=skills, metric="rmse"))
print()
print("Item Order Effect")
print(
model.crossvalidate(data_path="data/as.csv",
skills=skills,
multipair=True,
metric="rmse")["rmse"].values)
import sys
sys.path.append('../')
import numpy as np
from pyBKT.models import Model
np.seterr(divide='ignore', invalid='ignore')
#only one skill is shown due to the high time complexity needed to fit the item order effect model
skills = ["Venn Diagram"]
model = Model(seed = 0, num_fits = 5)
print("BKT")
print(model.crossvalidate(data_path = "data/as.csv", skills = skills, metric = "rmse"))
print(model.params())
print()
print("Item Order Effect")
print(model.crossvalidate(data_path = "data/as.csv", skills = skills, multipair = True, metric = "rmse"))
print(model.params().to_string())
import sys
sys.path.append('../')
import numpy as np
from pyBKT.models import Model
np.seterr(divide='ignore', invalid='ignore')
model = Model(seed=0, num_fits=20)
model.fit(data_path="data/builder_train_preprocessed.csv")
model.evaluate(data_path="data/builder_test_preprocessed.csv")
model2 = Model(seed=0, num_fits=20)
model2.fit(data_path="data/builder_train_preprocessed.csv", forgets=True)
model2.evaluate(data_path="data/builder_test_preprocessed.csv")
def prediction_code():
data = pd.read_csv('updated_data.csv')
model = Model(seed=42, num_fits=6)
data['skill_name'] = data['subCategory']
model.fit(data=data)
return model
maes = []
all_files.sort()
for i in all_files:
if i == "README.txt" or i == ".DS_Store":
continue
print("Creating model for ", i)
df0 = pd.read_csv("./data/glops-exact-processed/" + i)
seq_length = round(len(df0) / len(df0["user_id"].unique()))
df_train = (df0.groupby('user_id').apply(
lambda x: x.iloc[:-1] if len(x) > 1 else x).reset_index(drop=True)
) #remove all but last element
model = Model(num_fits=10, seed=2020)
model.fit(data=df_train)
predictions = model.predict(data=df0)
y_pred = predictions["correct_predictions"][seq_length - 1::seq_length]
y_true = df0["correct"][seq_length - 1::seq_length]
bkt_mae = sk.mean_absolute_error(y_true, y_pred)
df0 = pd.read_csv("./data/glops-exact-processed/" + i)
seq_length = round(len(df0) / len(df0["user_id"].unique()))
df_train = (df0.groupby('user_id').apply(
lambda x: x.iloc[:-1] if len(x) > 1 else x).reset_index(drop=True)
) #remove all but last element
model2 = Model(num_fits=10, seed=2020)