Upload 10 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Langkah[[:space:]]deployment[[:space:]]huggingface.docx filter=lfs diff=lfs merge=lfs -text

Langkah deployment huggingface.docx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1985069be28c22236f454b5a98e56bff6c0c05186729bdccec63231bbe193244
+size 4460836

klasifikasi-model.py

@@ -0,0 +1,70 @@
+# Mengimpor library
+import pandas as pd
+from PIL import Image
+import requests
+from io import BytesIO
+import streamlit as st
+import pickle
+
+# Menghilangkan warning
+import warnings
+warnings.filterwarnings("ignore")
+
+# Menulis judul
+st.markdown("<h1 style='text-align: center; '> Model Klasifikasi (Beli/Tidak) </h1>", unsafe_allow_html=True)
+st.markdown('---'*10)
+
+
+# Fungsi untuk prediksi
+def final_prediction(values, model):
+    global prediction
+    prediction = model.predict(values)
+    return prediction
+
+# Ini merupakan fungsi utama
+def main():
+    
+    # Nilai awal
+    usia = 25
+    gaji = 80000
+    
+    with st.container():
+        col1, col2 = st.columns(2)
+        with col1:
+            usia = st.number_input('Usia', value=usia)
+        with col2:
+            gaji = st.number_input('Estimasi Gaji', value=gaji)
+    
+    
+    st.markdown('---'*10)
+    
+    kelamin = st.selectbox('Jenis Kelamin', ('Laki', 'Perempuan'))
+    
+    data = {
+        'Kelamin': kelamin,
+        'Usia':usia,
+        'EstimasiGaji': gaji
+        }
+    
+    kolom = list(data.keys())
+    
+    df_final = pd.DataFrame([data.values()],columns=kolom)
+    
+    # load model
+    my_model = pickle.load(open('model_klasifikasi_terbaik.pkl', 'rb'))
+    
+    # Predict
+    result = int(final_prediction(df_final, my_model))
+    
+    hasil = []
+    if result==0:
+        hasil='Tidak Beli'
+    else:
+        hasil='Beli'
+    
+    st.markdown('---'*10)
+    
+    st.write('<center><b><h3>Predicted Beli/Tidak= ', hasil,'</b></h3>', unsafe_allow_html=True)
+           
+if __name__ == '__main__':
+	main() 

model_klasifikasi_terbaik.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a8fdc89c90172d74e87ff3872572bd3df1362adc419e42a311a656787586d7
+size 35643

model_regresi_terbaik.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af9cd6f82edd214dba16a106f1b8d361ef2bd59fc9b760050dd3271a187c6e4
+size 485271

perintah deploy azure.txt

@@ -0,0 +1 @@
+python -m streamlit run app.py --server.port 8000 --server.address 0.0.0.0

regresi-model.py

@@ -0,0 +1,65 @@
+# Mengimpor library
+import pandas as pd
+import streamlit as st
+import pickle
+
+# Menghilangkan warning
+import warnings
+warnings.filterwarnings("ignore")
+
+# Menulis judul
+st.markdown("<h1 style='text-align: center; '> Model Regresi </h1>", unsafe_allow_html=True)
+st.markdown('---'*10)
+
+
+# Fungsi untuk prediksi
+def final_prediction(values, model):
+    global prediction
+    prediction = model.predict(values)
+    return prediction
+
+# Ini merupakan fungsi utama
+def main():
+    
+    # Nilai awal
+    rd = 150000.2
+    adm = 140000.3
+    mkt = 300000.1
+    
+    with st.container():
+        col1, col2, col3 = st.columns(3)
+        with col1:
+            rd = st.number_input('R&D', value=rd)
+        with col2:
+            adm = st.number_input('Administrasi', value=adm)
+        with col3:
+           mkt = st.number_input('Marketing', value=mkt)
+    
+    
+    st.markdown('---'*10)
+    
+    wly = st.selectbox('Lokasi', ('New York', 'California', 'Florida'))
+    
+    data = {
+        'R&D': rd,
+        'Administrasi': adm,
+        'Marketing': mkt,
+        'Wilayah': wly,
+        }
+    
+    kolom = list(data.keys())
+    
+    df_final = pd.DataFrame([data.values()],columns=kolom)
+    
+    # load model
+    my_model = pickle.load(open('model_regresi_terbaik.pkl', 'rb'))
+    
+    # Predict
+    result = round(float(final_prediction(df_final, my_model)),2)
+    
+    st.markdown('---'*10)
+    
+    st.write('<center><b><h3>Predicted Profit= ', result,'</b></h3>', unsafe_allow_html=True)
+           
+if __name__ == '__main__':
+	main() 

solusi streamlit.txt

@@ -0,0 +1,7 @@
+1. Cari streamlit-script.py
+dia ada di folder anaconda3
+
+2. ubah 
+from streamlit.cli import main
+menjadi 
+from streamlit.web.cli import main