diff --git a/dashboard/__pycache__/overview.cpython-312.pyc b/dashboard/__pycache__/overview.cpython-312.pyc
index 8f2f26704cc6e3bfa9550e84daca8bd42c99817e..321b88fb7c5348f1282cb7d830f742620755193b 100644
Binary files a/dashboard/__pycache__/overview.cpython-312.pyc and b/dashboard/__pycache__/overview.cpython-312.pyc differ
diff --git a/dashboard/__pycache__/test_functions.cpython-312-pytest-7.4.4.pyc b/dashboard/__pycache__/test_functions.cpython-312-pytest-7.4.4.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..7b251e8ae104625150abdd6fdcdb1aab1d7d6bf2
Binary files /dev/null and b/dashboard/__pycache__/test_functions.cpython-312-pytest-7.4.4.pyc differ
diff --git a/dashboard/overview.py b/dashboard/overview.py
index 53bedb6ccf9b492d412f8f27f420e605c7d9a2ec..4348d7562bc22eb897fb701c25576fe92ae3cd9f 100644
--- a/dashboard/overview.py
+++ b/dashboard/overview.py
@@ -18,9 +18,25 @@ def data_overview():
if dataset_choice == "Selected Features":
st.subheader("Selected Features Dataset")
st.dataframe(df_filtered)
+
+ #option to download the datase
+ csv = df_filtered.to_csv(index=False).encode('utf-8')
+ st.download_button(
+ label="Download Selected Features CSV",
+ data=csv,
+ file_name='selected_features.csv',
+ mime='text/csv')
else:
st.subheader("Full Dataset")
st.dataframe(df_full)
+
+ csv = df_full.to_csv(index=False).encode('utf-8')
+ st.download_button(
+ label="Download Full Dataset CSV",
+ data=csv,
+ file_name='full_dataset.csv',
+ mime='text/csv')
+
st.subheader("Diagnosis Distribution")
fig = plot_distribution(df_full)
diff --git a/dashboard/svc_model.pkl b/dashboard/svc_model.pkl
index 1211b96082066ce1860ec90dee3b7c028dedb81c..993875ad9624a1a5d5d9defc956661a4f656d2ae 100644
Binary files a/dashboard/svc_model.pkl and b/dashboard/svc_model.pkl differ
diff --git a/dashboard/test_functions.py b/dashboard/test_functions.py
new file mode 100644
index 0000000000000000000000000000000000000000..3bf110fb7216ba56c34a9509f147099760ae31b4
--- /dev/null
+++ b/dashboard/test_functions.py
@@ -0,0 +1,35 @@
+import pytest
+import pandas as pd
+from visuals import load_full_data, create_grouped_features, plot_distribution, plot_correlation_with_diagnosis
+
+# Test Data Loading
+def test_load_full_data():
+ df = load_full_data()
+ assert isinstance(df, pd.DataFrame)
+ assert not df.empty
+ assert "Diagnosis" in df.columns
+
+# Test Feature Grouping
+def test_create_grouped_features():
+ df = load_full_data()
+ grouped = create_grouped_features(df)
+ assert isinstance(grouped, dict)
+ assert "Cognitive" in grouped
+ assert isinstance(grouped["Cognitive"], pd.DataFrame)
+
+# Test Distribution Plotting
+def test_plot_distribution_returns_figure():
+ df = load_full_data()
+ fig = plot_distribution(df)
+ assert fig is not None
+ assert hasattr(fig, "savefig")
+
+# Test Correlation Plotting
+def test_plot_correlation_with_diagnosis():
+ df = load_full_data()
+ groups = create_grouped_features(df)
+ y = df["Diagnosis"]
+ group_df = groups["Clinical"]
+ fig = plot_correlation_with_diagnosis(group_df, y, "Clinical")
+ assert fig is not None
+ assert hasattr(fig, "savefig")
diff --git a/models.ipynb b/models.ipynb
index a8ee4d9fe10b4d070cc078142c15cf28135ab078..0b7a5e1a19eba599d2dd560f10e7966d43bd8e4b 100644
--- a/models.ipynb
+++ b/models.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 161,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -20,12 +20,13 @@
"from sklearn.model_selection import cross_val_score, KFold\n",
"from sklearn.svm import SVC\n",
"from scipy.stats import randint\n",
- "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score"
+ "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score\n",
+ "import pickle"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 23,
"metadata": {},
"outputs": [
{
@@ -156,7 +157,7 @@
"9 ['BehavioralProblems', 'DifficultyCompletingTa... "
]
},
- "execution_count": 162,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
@@ -169,7 +170,7 @@
},
{
"cell_type": "code",
- "execution_count": 163,
+ "execution_count": 24,
"metadata": {},
"outputs": [
{
@@ -183,7 +184,7 @@
" 'MMSE']"
]
},
- "execution_count": 163,
+ "execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
@@ -197,7 +198,7 @@
},
{
"cell_type": "code",
- "execution_count": 164,
+ "execution_count": 25,
"metadata": {},
"outputs": [
{
@@ -583,7 +584,7 @@
"[2149 rows x 35 columns]"
]
},
- "execution_count": 164,
+ "execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
@@ -595,7 +596,7 @@
},
{
"cell_type": "code",
- "execution_count": 165,
+ "execution_count": 26,
"metadata": {},
"outputs": [
{
@@ -774,7 +775,7 @@
"[2149 rows x 7 columns]"
]
},
- "execution_count": 165,
+ "execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
@@ -787,7 +788,7 @@
},
{
"cell_type": "code",
- "execution_count": 166,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -835,7 +836,7 @@
},
{
"cell_type": "code",
- "execution_count": 167,
+ "execution_count": 28,
"metadata": {},
"outputs": [
{
@@ -865,7 +866,7 @@
},
{
"cell_type": "code",
- "execution_count": 168,
+ "execution_count": 29,
"metadata": {},
"outputs": [
{
@@ -902,7 +903,7 @@
},
{
"cell_type": "code",
- "execution_count": 169,
+ "execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
@@ -926,7 +927,7 @@
},
{
"cell_type": "code",
- "execution_count": 170,
+ "execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
@@ -970,7 +971,7 @@
},
{
"cell_type": "code",
- "execution_count": 171,
+ "execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
@@ -999,7 +1000,7 @@
},
{
"cell_type": "code",
- "execution_count": 172,
+ "execution_count": 33,
"metadata": {},
"outputs": [
{
@@ -1143,7 +1144,7 @@
},
{
"cell_type": "code",
- "execution_count": 173,
+ "execution_count": 34,
"metadata": {},
"outputs": [
{
@@ -1202,7 +1203,7 @@
],
"source": [
"\n",
- "modelsvc = SVC(kernel='rbf', gamma='auto', C=10)\n",
+ "modelsvc = SVC(kernel='rbf', gamma='auto', C=10, probability=True)\n",
"modelsvc.fit(X_train_scaled, y_train)\n",
"y_predsvc = modelsvc.predict(X_test_scaled)\n",
"accuracysvc = accuracy_score(y_test, y_predsvc)\n",
@@ -1281,7 +1282,7 @@
},
{
"cell_type": "code",
- "execution_count": 174,
+ "execution_count": 35,
"metadata": {},
"outputs": [
{
@@ -1419,7 +1420,7 @@
},
{
"cell_type": "code",
- "execution_count": 175,
+ "execution_count": 36,
"metadata": {},
"outputs": [
{
@@ -1432,7 +1433,7 @@
" 'F1-Score': [0.9531150398295376, 0.9273908901898491, 0.9461287249795657]}"
]
},
- "execution_count": 175,
+ "execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
@@ -1443,7 +1444,7 @@
},
{
"cell_type": "code",
- "execution_count": 176,
+ "execution_count": 37,
"metadata": {},
"outputs": [
{
@@ -1517,7 +1518,7 @@
},
{
"cell_type": "code",
- "execution_count": 177,
+ "execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
@@ -1533,17 +1534,17 @@
},
{
"cell_type": "code",
- "execution_count": 178,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
- "# import pickle\n",
+ "\n",
"# # Save models\n",
"# with open(\"rf_model.pkl\", \"wb\") as f:\n",
"# pickle.dump(modelr, f)\n",
"\n",
- "# with open(\"svc_model.pkl\", \"wb\") as f:\n",
- "# pickle.dump(modelsvc, f)\n",
+ "#with open(\"svc_model.pkl\", \"wb\") as f:\n",
+ " #pickle.dump(modelsvc, f)\n",
"\n",
"# with open(\"dt_model.pkl\", \"wb\") as f:\n",
"# pickle.dump(modeld, f)\n"
@@ -1551,7 +1552,7 @@
},
{
"cell_type": "code",
- "execution_count": 179,
+ "execution_count": 40,
"metadata": {},
"outputs": [],
"source": [
@@ -1562,7 +1563,7 @@
},
{
"cell_type": "code",
- "execution_count": 180,
+ "execution_count": 41,
"metadata": {},
"outputs": [
{
@@ -1575,7 +1576,7 @@
" 'F1-Score': [0.9531150398295376, 0.9273908901898491, 0.9461287249795657]}"
]
},
- "execution_count": 180,
+ "execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
diff --git a/requirements.txt b/requirements.txt
index 74d8ac9b16aa965e7b59055cb4cc63dca78f3568..2def18ebde8b6d4042bca573997cf49b3994c58e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -7,3 +7,5 @@ Pillow
scikit-learn
scipy
deap
+pytest
+pickle