submission

eda.py

@@ -22,14 +22,14 @@ def run():
 
     # Menambahkan Deskripsi
     st.write('## Background')
-    st.write('Hepatitis C is a very dangerous and contagious disease, which is caused by the Hepatitis C virus (HCV).' 
-    ' Transmission of Hepatitis C can be through body fluids, blood, or when having sex with sufferers.' 
-    ' Usually, the symptoms of Hepatitis C are not visible, so suddenly the sufferer or patient has experienced the chronic stage of hepatitis.' 
-    ' Hepatitis C can also trigger the onset of fibrosis which causes cirrhosis and liver cancer.'
+    st.write(""" Hepatitis C is a very dangerous and contagious disease, which is caused by the Hepatitis C virus (HCV). 
+    Transmission of Hepatitis C can be through body fluids, blood, or when having sex with sufferers. 
+    Usually, the symptoms of Hepatitis C are not visible, so suddenly the sufferer or patient has experienced the chronic stage of hepatitis. 
+    Hepatitis C can also trigger the onset of fibrosis which causes cirrhosis and liver cancer.
 
-    ' Therefore, the Liver Hospital must have adequate facilities and treatment to treat patients with indications and symptoms of Hepatitis C.' 
-    ' The purpose of this data classification analysis and modeling is to find out what the diagnoses are in patients so that they receive further treatment, can be cured, and minimize death.' 
-    ' This modeling uses 4 Machine Learning (Supervised) algorithms, namely Logistic Regression, Support Vector Machine, Random Forest, and Gradient Boosting to get the best predictions with hyperparameter tuning.')
+    Therefore, the Liver Hospital must have adequate facilities and treatment to treat patients with indications and symptoms of Hepatitis C. 
+    The purpose of this data classification analysis and modeling is to find out what the diagnoses are in patients so that they receive further treatment, can be cured, and minimize death. 
+    This modeling uses 4 Machine Learning (Supervised) algorithms, namely Logistic Regression, Support Vector Machine, Random Forest, and Gradient Boosting to get the best predictions with hyperparameter tuning.""")
 
     st.write('## Dataset')
     st.write("""
@@ -66,6 +66,40 @@ def run():
     sns.countplot(x='Category', data=df1, palette="PuRd")
     st.pyplot(fig)
 
+    st.write('#### Sex Based on Diagnose')
+    fig1, ax1 = plt.subplots(figsize=(15, 8))
+    sns.countplot(x='Sex', hue='Category', data=df1, ax=ax1)
+    st.pyplot(fig1)
+
+    # Mengelompokkan Usia
+    bins = [18, 30, 40, 50, 60, 70, 120]
+    labels = ['20-29', '30-39', '40-49', '50-59', '60-69', '70-80']
+    df1['agerange'] = pd.cut(df1.Age, bins, labels = labels,include_lowest = True)
+
+    # Menampilkan visualisasi usia berdasarkan diagnosis
+    st.write('#### Age Based on Diagnose')
+    fig2, ax2 = plt.subplots(figsize=(10,7))
+    sns.countplot(x='agerange', data=df1, hue="Category", ax=ax2)
+    st.pyplot(fig2)
+
+    # Rata-rata AST berdasarkan diagnosis
+    AST = df1.groupby('Category').agg({'AST':'mean'}).reset_index()
+    AST = AST.sort_values(by='AST')
+    # Menampilkan visualisasi bar chart
+    st.write('#### AST Mean Based on Diagnose')
+    fig3, ax3 = plt.subplots(figsize=(10,7))
+    sns.barplot(data=AST, x=AST.Category, y=AST.AST, ax=ax3)
+    st.pyplot(fig3)
+
+    # Rata-rata CHE berdasarkan diagnosis
+    CHE = df1.groupby('Category').agg({'CHE':'mean'}).reset_index()
+    CHE = CHE.sort_values(by='CHE')
+    # Menampilkan visualisasi bar chart
+    st.write('#### CHE Mean Based on Diagnose')
+    fig4, ax4 = plt.subplots(figsize=(10,7))
+    sns.barplot(data=CHE, x=CHE.Category, y=CHE.CHE, ax=ax4)
+    st.pyplot(fig4)
+
     # Membuat heatmap correlation
     st.write('#### Heatmap Correlation')
     fig = plt.figure(figsize = (15,8))

prediction.py

@@ -26,24 +26,25 @@ with open('enc_columns.txt', 'r') as file_6:
 
 def run():
     with st.form(key='Hepatitis_C_Prediction'):
-        Category = st.selectbox('Category', (0, 1, 2, 3, 4), index=1)
+        Category = st.selectbox('Category', ('0=Blood Donor', '1=suspect Blood Donor', 
+                                             '2=Hepatitis', '3=Fibrosis', '4=Chirrosis'), index=1)
         Age = st.number_input('Age', min_value=23, max_value=80, value=23)
-        Sex = st.selectbox('Sex', ('m', 'f'), index=1)
+        Sex = st.selectbox('Sex', ('Male', 'Female'), index=1)
         st.markdown('---')
 
-        ALB = st.number_input('ALB', min_value=0, max_value=500, value=0)
-        ALP = st.number_input('ALP', min_value=0, max_value=500, value=0)
-        ALT = st.number_input('ALT', min_value=0, max_value=500, value=0)
-        AST = st.number_input('AST', min_value=0, max_value=500, value=0)
-        BIL = st.number_input('BIL', min_value=0, max_value=500, value=0)
+        ALB = st.number_input('ALB', min_value=0, max_value=85, value=0)
+        ALP = st.number_input('ALP', min_value=0, max_value=420, value=0)
+        ALT = st.number_input('ALT', min_value=0, max_value=325, value=0)
+        AST = st.number_input('AST', min_value=0, max_value=325, value=0)
+        BIL = st.number_input('BIL', min_value=0, max_value=210, value=0)
 
         st.markdown('---')
 
-        CHE = st.number_input('CHE', min_value=0, max_value=100, value=0)
-        CHOL = st.number_input('CHOL', min_value=0, max_value=100, value=0)
-        CREA = st.number_input('CREA', min_value=0, max_value=1000, value=0)
-        GGT = st.number_input('GGT', min_value=0, max_value=1000, value=0)
-        PROT = st.number_input('PROT', min_value=0, max_value=1000, value=0)
+        CHE = st.number_input('CHE', min_value=0, max_value=20, value=0)
+        CHOL = st.number_input('CHOL', min_value=0, max_value=10, value=0)
+        CREA = st.number_input('CREA', min_value=0, max_value=1080, value=0)
+        GGT = st.number_input('GGT', min_value=0, max_value=651, value=0)
+        PROT = st.number_input('PROT', min_value=0, max_value=87, value=0)
 
         submitted = st.form_submit_button('Predict')