Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -93,6 +93,7 @@ if page == "Clustering Analysis":
|
|
93 |
else:
|
94 |
insurance_claims = pd.read_csv(selected_csv)
|
95 |
|
|
|
96 |
insurance_claims.describe().T
|
97 |
|
98 |
cat_col = insurance_claims.select_dtypes(include=['object']).columns
|
@@ -104,6 +105,7 @@ if page == "Clustering Analysis":
|
|
104 |
# Create a Matplotlib figure
|
105 |
fig, ax = plt.subplots(figsize=(12, 8))
|
106 |
# Create a heatmap using seaborn
|
|
|
107 |
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt='.2f', ax=ax)
|
108 |
# Set the title for the heatmap
|
109 |
ax.set_title('Correlation Heatmap')
|
@@ -133,15 +135,19 @@ if page == "Clustering Analysis":
|
|
133 |
cluster_summary = cluster_model_2.groupby('Cluster').agg(['count', 'mean', 'median', 'min', 'max',
|
134 |
'std', 'var', 'sum', ('quantile_25', lambda x: x.quantile(0.25)),
|
135 |
('quantile_75', lambda x: x.quantile(0.75)), 'skew'])
|
|
|
136 |
cluster_summary
|
|
|
137 |
cluster_model_2
|
138 |
|
139 |
# all_metrics = get_metrics()
|
140 |
# all_metrics
|
141 |
|
|
|
142 |
cluster_results = pull()
|
143 |
cluster_results
|
144 |
|
|
|
145 |
# plot pca cluster plot
|
146 |
plot_model(cluster_model, plot = 'cluster', display_format = 'streamlit')
|
147 |
|
@@ -160,6 +166,20 @@ if page == "Clustering Analysis":
|
|
160 |
if selected_model != 'ap':
|
161 |
plot_model(cluster_model, plot = 'distribution', display_format = 'streamlit')
|
162 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
elif page == "Anomaly Detection":
|
164 |
st.header('Anomaly Detection')
|
165 |
|
@@ -221,12 +241,29 @@ elif page == "Anomaly Detection":
|
|
221 |
# train model
|
222 |
anomaly_model = create_model(selected_model)
|
223 |
|
|
|
224 |
anomaly_model_2 = assign_model(anomaly_model)
|
225 |
anomaly_model_2
|
226 |
|
|
|
227 |
anomaly_results = pull()
|
228 |
anomaly_results
|
229 |
|
230 |
# plot
|
|
|
231 |
plot_model(anomaly_model, plot = 'tsne', display_format = 'streamlit')
|
232 |
-
plot_model(anomaly_model, plot = 'umap', display_format = 'streamlit')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
else:
|
94 |
insurance_claims = pd.read_csv(selected_csv)
|
95 |
|
96 |
+
st.header("Inference Description")
|
97 |
insurance_claims.describe().T
|
98 |
|
99 |
cat_col = insurance_claims.select_dtypes(include=['object']).columns
|
|
|
105 |
# Create a Matplotlib figure
|
106 |
fig, ax = plt.subplots(figsize=(12, 8))
|
107 |
# Create a heatmap using seaborn
|
108 |
+
st.header("Heat Map")
|
109 |
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt='.2f', ax=ax)
|
110 |
# Set the title for the heatmap
|
111 |
ax.set_title('Correlation Heatmap')
|
|
|
135 |
cluster_summary = cluster_model_2.groupby('Cluster').agg(['count', 'mean', 'median', 'min', 'max',
|
136 |
'std', 'var', 'sum', ('quantile_25', lambda x: x.quantile(0.25)),
|
137 |
('quantile_75', lambda x: x.quantile(0.75)), 'skew'])
|
138 |
+
st.header("Cluster Summary")
|
139 |
cluster_summary
|
140 |
+
st.header("Assign Model")
|
141 |
cluster_model_2
|
142 |
|
143 |
# all_metrics = get_metrics()
|
144 |
# all_metrics
|
145 |
|
146 |
+
st.header("Clustering Metrics")
|
147 |
cluster_results = pull()
|
148 |
cluster_results
|
149 |
|
150 |
+
st.header("Clustering Plots")
|
151 |
# plot pca cluster plot
|
152 |
plot_model(cluster_model, plot = 'cluster', display_format = 'streamlit')
|
153 |
|
|
|
166 |
if selected_model != 'ap':
|
167 |
plot_model(cluster_model, plot = 'distribution', display_format = 'streamlit')
|
168 |
|
169 |
+
# Create a Classification Model to extract feature importance
|
170 |
+
st.header("Feature Importance")
|
171 |
+
from pycaret.classification import *
|
172 |
+
s = setup(cluster_model_2, target = 'Cluster')
|
173 |
+
lr = create_model('lr')
|
174 |
+
# this is how you can recreate the table
|
175 |
+
feat_imp = pd.DataFrame({'Feature': get_config('X_train').columns, 'Value' : abs(lr.coef_[0])}).sort_values(by='Value', ascending=False)
|
176 |
+
# sort by feature importance value and filter top 10
|
177 |
+
feat_imp = feat_imp.sort_values(by='Value', ascending=False).head(10)
|
178 |
+
# Display the filtered table in Streamlit
|
179 |
+
# st.dataframe(feat_imp)
|
180 |
+
# Display the filtered table as a bar chart in Streamlit
|
181 |
+
st.bar_chart(feat_imp.set_index('Feature'))
|
182 |
+
|
183 |
elif page == "Anomaly Detection":
|
184 |
st.header('Anomaly Detection')
|
185 |
|
|
|
241 |
# train model
|
242 |
anomaly_model = create_model(selected_model)
|
243 |
|
244 |
+
st.header("Assign Model")
|
245 |
anomaly_model_2 = assign_model(anomaly_model)
|
246 |
anomaly_model_2
|
247 |
|
248 |
+
st.header("Anomaly Metrics")
|
249 |
anomaly_results = pull()
|
250 |
anomaly_results
|
251 |
|
252 |
# plot
|
253 |
+
st.header("Anomaly Plots")
|
254 |
plot_model(anomaly_model, plot = 'tsne', display_format = 'streamlit')
|
255 |
+
plot_model(anomaly_model, plot = 'umap', display_format = 'streamlit')
|
256 |
+
|
257 |
+
# Create a Classification Model to extract feature importance
|
258 |
+
st.header("Feature Importance")
|
259 |
+
from pycaret.classification import *
|
260 |
+
s = setup(anomaly_model_2, target = 'Anomaly')
|
261 |
+
lr = create_model('lr')
|
262 |
+
# this is how you can recreate the table
|
263 |
+
feat_imp = pd.DataFrame({'Feature': get_config('X_train').columns, 'Value' : abs(lr.coef_[0])}).sort_values(by='Value', ascending=False)
|
264 |
+
# sort by feature importance value and filter top 10
|
265 |
+
feat_imp = feat_imp.sort_values(by='Value', ascending=False).head(10)
|
266 |
+
# Display the filtered table in Streamlit
|
267 |
+
# st.dataframe(feat_imp)
|
268 |
+
# Display the filtered table as a bar chart in Streamlit
|
269 |
+
st.bar_chart(feat_imp.set_index('Feature'))
|