def clustering():
st.markdown("## **Master's Project**")
st.markdown('---')
st.markdown("# **Unsupervised Learning | Clustering**")
st.markdown("### Choose a Dataset")
files = tools.get_files()
option = st.selectbox('Select a Teacher Answer', files['name'])
index = files['name'].index(option)
st.write('You selected:', index)
doc = files['doc'][index]
data = files['data'][index]
st.markdown("## Modeling Example")
st.markdown('**Select the below based on what you want to see:**')
doc_flag = st.checkbox('Display Question Info')
data_flag = st.checkbox('Display Prediction Data')
chart_flag = st.checkbox('Display Reduced-Dimensionality Chart')
model_flag = st.checkbox('Display Model Info and Performance')
nlp = Clustering_NLP(data, doc)
nlp.correct_cluster_labels()
if doc_flag:
st.markdown('## Question Info')
st.write(doc)
if data_flag:
st.write(data.columns)
st.markdown('## Prediction Data')
st.write(data)
st.write(pd.Series(data.columns, name='Features'))
if chart_flag:
col1, col2 = st.beta_columns(2)
fig1, ax1 = charts.plot_pca_chart(data, doc['label'],
nlp.model.cluster_centers_)
fig2, ax2 = charts.plot_tsne_chart(data, doc['label'],
nlp.model.cluster_centers_)
with col1:
st.pyplot(fig=fig1)
with col2:
st.pyplot(fig=fig2)
if model_flag:
st.markdown('## Model Data')
st.markdown(f'### **Accuracy of Model: {round(nlp.accuracy(),3)}** ')
st.pyplot(fig=charts.plot_confusion_matrix(nlp.doc['label'],
nlp.doc.cluster))
results = doc[['student_answer', 'label', 'cluster']]
try_it = st.checkbox('Try it Yourself!')
explore_flag = st.checkbox('Explore Data')
if try_it:
tryit(nlp)
if explore_flag:
st.markdown(f"""**Dataset Length: {len(results)}** """)
start, end = st.slider(label='Data View Select',
min_value=0,
max_value=len(nlp.doc) - 1,
value=(0, 5))
st.markdown(
f"""**Teacher Answer: {nlp.doc['teacher_answer'].values[0]}**"""
)
for i in range(int(start), int(end) + 1):
st.markdown(
f"""{i}. {'Label:':>10} {str(nlp.doc.loc[i,'label'])} Pred: {str(nlp.doc.loc[i,'cluster'])} {str(nlp.doc.loc[i,'student_answer'])}"""
)
def clustering():
st.markdown("## **Master's Project**")
st.markdown('---')
st.markdown("# **Unsupervised Learning | Clustering**")
st.markdown("### Choose a Dataset")
option = st.selectbox(
'Select a Teacher Answer',
files['name']
)
index = files['name'].index(option)
st.write('You selected:', index)
doc= files['doc'][index]
data= files['data'][index]
st.markdown("## Modeling Example")
st.markdown('**Select the below based on what you want to see:**')
chart_flag = st.checkbox('Display Reduced-Dimensionality Chart')
model_flag = st.checkbox('Display Model Info and Performance')
nlp = Clustering_NLP(data, doc)
nlp.correct_cluster_labels()
if chart_flag:
col1, col2 = st.beta_columns(2)
fig1, ax1 = charts.plot_pca_chart(data, doc['label'], nlp.model.cluster_centers_)
fig2, ax2 = charts.plot_tsne_chart(data, doc['label'], nlp.model.cluster_centers_)
with col1:
st.pyplot(fig = fig1)
with col2:
st.pyplot(fig = fig2)
if model_flag:
st.markdown('## Model Data Metrics')
scores = {}
scores['Accuracy'] = round(nlp.accuracy(),3)
scores['Balanced Accuract'] = round(nlp.balanced_accuracy(), 3)
scores['F1 Score'] = round(nlp.f1_scorer(), 3)
scores['Cohens Kappa'] = round(nlp.kappa(), 3)
scores = pd.DataFrame.from_dict(scores, orient = 'index').transpose()
scores.rename(index = {0:"Scores"}, inplace = True)
st.table(scores)
st.pyplot(fig = charts.plot_confusion_matrix(nlp.doc['label'], nlp.doc.cluster))
results = doc[['student_answer', 'label', 'cluster']]
try_it = st.checkbox('Try it Yourself!')
explore_flag = st.checkbox('Explore Data')
if try_it:
tryit(nlp, 'cluster')
if explore_flag:
st.markdown(f"""**Dataset Length: {len(results)}** """)
start, end = st.slider(
label = 'Data View Select',
min_value = 0,
max_value = len(nlp.doc)-1,
value = (0,5)
)
st.markdown(f"""**Teacher Answer: {nlp.doc['teacher_answer'].values[0]}**""")
for i in range(int(start),int(end)+1):
st.markdown(f"""{i}. {'Label:':>10} {str(nlp.doc.loc[i,'label'])} Pred: {str(nlp.doc.loc[i,'cluster'])} {str(nlp.doc.loc[i,'student_answer'])}""")
def classification():
st.markdown("## **Master's Project**")
st.markdown('---')
st.markdown("# **Supervised Learning | Classification**")
st.markdown("### Choose a Dataset")
files = tools.get_files()
option = st.selectbox('Select a Teacher Answer', files['name'])
index = files['name'].index(option)
st.write('You selected:', index)
doc = files['doc'][index]
data = files['data'][index]
st.markdown("## Modeling Example")
st.markdown('**Select the below based on what you want to see:**')
doc_flag = st.checkbox('Display Question Info')
data_flag = st.checkbox('Display Prediction Data')
model_flag = st.checkbox('Display Model Info and Performance')
test_size = st.number_input('Test Size',
min_value=0.01,
max_value=0.91,
value=.75,
step=0.05)
nlp = Classification_NLP(data, doc, test_size)
st.markdown(f'Training Set Size: {len(nlp.X_train)}')
st.markdown(f'Test Set Size: {len(nlp.X_test)}')
if doc_flag:
st.markdown('## Question Info')
st.write(doc)
if data_flag:
st.markdown('## Prediction Data')
st.write(data)
st.write(pd.Series(data.columns, name='Features'))
if model_flag:
st.markdown('## Model Data')
_, accuracy = nlp.accuracy()
st.markdown(
f'### **Test Set Accuracy of Model: {round(accuracy, 3)}** ')
st.pyplot(fig=charts.plot_confusion_matrix(nlp.y_test, nlp.pred))
results = doc[['student_answer', 'label', 'prediction']]
try_it = st.checkbox('Try it Yourself!')
explore_flag = st.checkbox('Explore Data')
if try_it:
tryit(nlp)
if explore_flag:
st.markdown(f"""**Dataset Length: {len(results)}** """)
start, end = st.slider(label='Data View Select',
min_value=0,
max_value=len(nlp.doc) - 1,
value=(0, 5))
st.markdown(
f"""**Teacher Answer: {nlp.doc['teacher_answer'].values[0]}**"""
)
for i in range(int(start), int(end) + 1):
if nlp.doc.loc[i, 'label'] != nlp.doc.loc[i, 'prediction']:
st.markdown(
f"""{i}. {'Label:':>10} {str(nlp.doc.loc[i,'label'])} Pred: {str(nlp.doc.loc[i,'prediction'])} {str(nlp.doc.loc[i,'student_answer'])}"""
)
else:
st.markdown(
f"""{i}. {'Label:':>10} {str(nlp.doc.loc[i,'label'])} Pred: {str(nlp.doc.loc[i,'prediction'])} {str(nlp.doc.loc[i,'student_answer'])}"""
)
def classification():
st.markdown("## **Master's Project**")
st.markdown('---')
st.markdown("# **Supervised Learning | Classification**")
st.markdown("### Choose a Dataset")
# files = tools.get_files()
option = st.selectbox(
'Select a Teacher Answer',
files['name']
)
index = files['name'].index(option)
st.write('You selected:', index)
doc= files['doc'][index]
data= files['data'][index]
st.markdown("## Modeling Example")
st.markdown('**Select the below based on what you want to see:**')
chart_flag = st.checkbox('Display Logistic Function Chart')
model_flag = st.checkbox('Display Model Info and Performance')
test_size = st.number_input(
'Test Size',
min_value = 0.01,
max_value = 0.91,
value = .75,
step = 0.05
)
nlp = Classification_NLP(data, doc, test_size)
st.markdown(f'Training Set Size: {len(nlp.X_train)}')
st.markdown(f'Test Set Size: {len(nlp.X_test)}')
if chart_flag:
st.pyplot(fig = charts.plot_logistic_function(nlp, test_size))
if model_flag:
st.markdown('## Model Data Metrics')
scores = {}
_, accuracy = nlp.accuracy()
scores['Accuracy'] = round(accuracy,3)
scores['Balanced Accuract'] = round(nlp.balanced_accuracy(), 3)
scores['F1 Score'] = round(nlp.f1_scorer(), 3)
scores['Cohens Kappa'] = round(nlp.kappa(), 3)
scores = pd.DataFrame.from_dict(scores, orient = 'index').transpose()
scores.rename(index = {0:"Scores"}, inplace = True)
st.table(scores)
st.pyplot(fig = charts.plot_confusion_matrix(nlp.doc.label, nlp.doc.prediction))
results = doc[['student_answer', 'label', 'prediction']]
try_it = st.checkbox('Try it Yourself!')
explore_flag = st.checkbox('Explore Data')
if try_it:
tryit(nlp, 'prediction')
if explore_flag:
st.markdown(f"""**Dataset Length: {len(results)}** """)
start, end = st.slider(
label = 'Data View Select',
min_value = 0,
max_value = len(nlp.doc)-1,
value = (0,5)
)
st.markdown(f"""**Teacher Answer: {nlp.doc['teacher_answer'].values[0]}**""")
for i in range(int(start),int(end)+1):
if nlp.doc.loc[i,'label'] != nlp.doc.loc[i,'prediction']:
st.markdown(f"""{i}. {'Label:':>10} {str(nlp.doc.loc[i,'label'])} Pred: {str(nlp.doc.loc[i,'prediction'])} {str(nlp.doc.loc[i,'student_answer'])}""")
else:
st.markdown(f"""{i}. {'Label:':>10} {str(nlp.doc.loc[i,'label'])} Pred: {str(nlp.doc.loc[i,'prediction'])} {str(nlp.doc.loc[i,'student_answer'])}""")