commit file

app.py

@@ -0,0 +1,10 @@
+import streamlit as st 
+import eda
+import prediction 
+
+navigation = st.sidebar.selectbox('Pilih Halaman : ', ('eda','Predict Death'))
+
+if navigation == 'eda':
+    eda.run()
+else:
+    prediction.run()

eda.py

@@ -0,0 +1,69 @@
+import streamlit as st 
+import pandas as pd 
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px 
+from PIL import Image
+
+st.set_page_config(
+    page_title = 'Death Prediction'
+)
+
+def run():
+
+    # Membuat Title 
+    st.title('Death Prediction Simulator')
+
+    #Sub header 
+    st.subheader('EDA untuk analisa Dataset Death Prediction') 
+
+    # Insert Gambar 
+    #image = Image.open('')
+    #st.image(image, caption ='Death Prediction')
+
+    # Menambahkan Deskripsi 
+    st.write('Page ini dibuat oleh Ferdiansyah Ersatiyo')
+
+    st.markdown('---')
+
+
+    #show dataframe 
+    data = pd.read_csv('https://raw.githubusercontent.com/FerdiErs/SQL/main/h8dsft_P1G3_Ferdiansyah_Ersatiyo.csv')
+    st.dataframe(data)
+
+    #membuat barplot jenis kelamin
+    st.write('### Plot Sex')
+    fig = plt.figure(figsize=(10,5))
+    ax = sns.countplot(x='sex', data=data, palette=['b', 'r'])
+    ax.bar_label(ax.containers[0])
+    st.pyplot(fig)
+
+    #membuat histogram umur 
+    st.write('### Histogram Umur')
+    fig = plt.figure(figsize=(10,5))
+    sns.histplot(data['age'],bins=20,kde=True)
+    st.pyplot(fig)
+
+    #membuat pie chart 
+    st.write('### Pie Chart Smoking')
+    a= data.smoking.value_counts()
+    def autopct_format(values):
+            def my_format(pct):
+                total = sum(values)
+                val = int(round(pct*total/100.0))
+                return '{:.1f}%\n({v:d})'.format(pct, v=val)
+            return my_format
+    fig = plt.figure(figsize=(5,5))
+    a.plot.pie(subplots=True, autopct=autopct_format(a))
+    st.pyplot(fig)
+
+    # Membuat Histogram berdasarkan input user 
+    st.write('### Histogram berdasarkan input user')
+    pilihan = st.selectbox('pilih column : ',['sex','smoking','diabetes', 'anaemia','high_blood_pressure'])
+    fig = plt.figure(figsize=(10,5))
+    ax = sns.countplot(x=data[pilihan])
+    ax.bar_label(ax.containers[0])
+    st.pyplot(fig)
+
+if __name__== '__main__':
+    run()

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b7bda6dba0f5ad1408f5e6aa7eebbd6183fe024898a1ec164d89f946e8e739
+size 203471

prediction.py

@@ -0,0 +1,57 @@
+import streamlit as st 
+import pandas as pd 
+import numpy as np 
+import pickle 
+import json 
+import joblib as jb
+
+#load models
+model = jb.load('model.pkl')
+
+def run():
+    with st.form('key=form_prediction') :
+        age = st.number_input('Age', min_value=40, max_value=95, value= 60, step=1, help='Usia anda')
+        anaemia = st.selectbox('Anemia',(0,1), index= 1)
+        creatinine_phosphokinase= st.number_input('creatinine_phosphokinase', min_value=23, max_value=7861)
+        diabetes = st.selectbox('Diabetes',(0,1), index= 1)
+        ejection_fraction = st.number_input('ejection_fraction', min_value=14, max_value=80)
+        high_blood_pressure = st.selectbox('Tekanan Darah',(0,1), index= 1) 
+        platelets = st.number_input('platelets', min_value=25100, max_value=850000)
+        serum_creatinine = st.number_input('serum creatinine',min_value=0.5,max_value=9.4)
+        serum_sodium = st.number_input('serum_sodium',min_value=113, max_value=148)
+        sex = st.selectbox('Jenis Kelamin',(0,1), index= 1) 
+        smoking = st.selectbox('smoking',(0,1), index= 1)
+        time =  st.slider('serum creatinine',4,135,285) 
+
+
+        submitted = st.form_submit_button('Predict')
+
+    data_inf = {
+    'age': age,
+    'anaemia': anaemia,
+    'creatinine_phosphokinase':creatinine_phosphokinase,
+    'diabetes':diabetes,
+    'ejection_fraction': ejection_fraction,
+    'high_blood_pressure': high_blood_pressure,
+    'platelets' :platelets,
+    'serum_creatinine' :serum_creatinine,
+    'serum_sodium' :serum_sodium,
+    'sex': sex,
+    'smoking':smoking,
+    'time': time
+    }
+
+    data_inf = pd.DataFrame([data_inf])
+    st.dataframe(data_inf)
+
+    if submitted:
+
+        # Predict using bagging 
+        y_pred_inf = model.predict(data_inf)
+
+        st.write('# Death Prediction : ', str(int(y_pred_inf)))
+
+
+if __name__=='__main__':
+    run()
+