Kalbe Deployment

app.py

@@ -0,0 +1,33 @@
+import streamlit as st
+import eda
+import prediction_a
+import prediction_b
+
+
+# Set Config dan icon
+st.set_page_config(
+        page_title='Sales Forecast Prediction',
+        layout='wide',
+        )
+
+# Hide Streamlit Style
+hide_streamlit_style = """
+            <style>
+            #MainMenu {visibility: hidden;}
+            footer {visibility: hidden;}
+            </style>
+            """
+st.markdown(hide_streamlit_style, unsafe_allow_html=True) 
+
+# Membuat navigasi
+st.sidebar.markdown("# Evan Derin Ihsanudin - RMT-FTDS-17")
+navigation = st.sidebar.selectbox('Pilih Halaman (Forecast Category A/Forecast Category B/EDA): ', ('Forecast Category A','Forecast Category B','Exploratory Data Analysis'))
+st.sidebar.image("https://imgur.com/qJ1Sryt.png", use_column_width=True)
+
+# Run modul dengan if else
+if navigation == 'Forecast Category A' :
+    prediction_a.run()
+elif navigation == 'Forecast Category B' :
+    prediction_b.run()
+else :
+    eda.run()

eda.py

@@ -0,0 +1,79 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+from PIL import Image
+
+
+# Load data dengan pandas dan assign ke variabel df
+xls = pd.ExcelFile('kalbe_data.xlsx')
+df_a1 = pd.read_excel(xls,'A1')
+df_a2 = pd.read_excel(xls,'A2')
+df_b1 = pd.read_excel(xls,'B1')
+df_b2 = pd.read_excel(xls,'B2')
+
+# Membuat df kategori A
+df_a = df_a1.copy()
+df_a.rename(columns = {'Sales':'Sales_A1'}, inplace = True)
+# Concat & rename
+df_a = pd.concat([df_a, df_a2['Sales']], axis=1)
+df_a.rename(columns = {'Sales':'Sales_A2'}, inplace = True)
+df_a.replace(np.nan, 0, inplace=True)
+# Menghitung total sales kategori A
+df_a['sales_total'] = df_a['Sales_A1'] + df_a['Sales_A2']
+# Membuat df kategori B
+df_b = df_b1.copy()
+df_b.rename(columns = {'Sales':'Sales_B1'}, inplace = True)
+# Concat & rename
+df_b = pd.concat([df_b, df_b2['Sales']], axis=1)
+df_b.rename(columns = {'Sales':'Sales_B2'}, inplace = True)
+df_b.replace(np.nan, 0, inplace=True)
+# Menghitung total sales kategori B
+df_b['sales_total'] = df_b['Sales_B1'] + df_b['Sales_B2']
+
+
+def run() :
+    # Membuat Title 
+    st.markdown("<h1 style='text-align: center;'>Exploratory Data Analysis</h1>", unsafe_allow_html=True)
+    st.write('Berikut adalah EDA dari setiap feature')
+
+    # Membuat Sub Header
+    st.subheader('**Trend Category A**')
+    fig = px.line(df_a, x=df_a.Day, y=df_a.sales_total)
+    fig.update_layout(xaxis_title="Day", yaxis_title="Actual Sales")
+    st.plotly_chart(fig)
+
+    # Membuat Sub Header
+    st.subheader('**Trend Category B**')
+    fig = px.line(df_b, x=df_b.Day, y=df_b.sales_total)
+    fig.update_layout(xaxis_title="Day", yaxis_title="Actual Sales")
+    st.plotly_chart(fig)
+
+    # Membuat Sub Header
+    st.subheader('**Trend Product A1**')
+    fig = px.line(df_a1, x=df_a1.Day, y=df_a1.Sales)
+    fig.update_layout(xaxis_title="Day", yaxis_title="Actual Sales")
+    st.plotly_chart(fig)
+
+    # Membuat Sub Header
+    st.subheader('**Trend Product A2**')
+    fig = px.line(df_a2, x=df_a2.Day, y=df_a2.Sales)
+    fig.update_layout(xaxis_title="Day", yaxis_title="Actual Sales")
+    st.plotly_chart(fig)
+
+    # Membuat Sub Header
+    st.subheader('**Trend Product B1**')
+    fig = px.line(df_b1, x=df_b1.Day, y=df_b1.Sales)
+    fig.update_layout(xaxis_title="Day", yaxis_title="Actual Sales")
+    st.plotly_chart(fig)
+
+    # Membuat Sub Header
+    st.subheader('**Trend Product B2**')
+    fig = px.line(df_b2, x=df_b2.Day, y=df_b2.Sales)
+    fig.update_layout(xaxis_title="Day", yaxis_title="Actual Sales")
+    st.plotly_chart(fig)
+
+if __name__ == '__main__':
+    run()

model_a.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e045da3cf1e2fb26e1bc6c243e17a944d5785a38654d431253e97108ed5980
+size 851642

model_a1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc2df4fb5ecb1b09f4e6811579e94aa48d9abaa3857d8345986bcb15100ed8e
+size 1768541

model_a2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdfb46e3d634ca36ad061725dc370c74ee67f182dabf05444fc87f4daf74a84
+size 1766783

model_b.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52420d72418244517acb237c9c50d6ab292bbccf6ad95b258eae13b5cda4c0c
+size 1516101

model_b1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4afde91bcf88f24198f02648afb29a13893cf6d5722483b16f0b150ba29c4b
+size 9872

model_b2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4afde91bcf88f24198f02648afb29a13893cf6d5722483b16f0b150ba29c4b
+size 9872

prediction_a.py

@@ -0,0 +1,81 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import matplotlib.pyplot as plt
+import plotly.express as px
+
+# Load Model Kategori A
+with open('model_a.pkl', 'rb') as file_1:
+  model_a = pickle.load(file_1)
+
+# Load Model Produk A1
+with open('model_a1.pkl', 'rb') as file_3:
+  model_a1 = pickle.load(file_3)
+
+# Load Model Produk A2
+with open('model_a2.pkl', 'rb') as file_4:
+  model_a2 = pickle.load(file_4)
+
+def run() :
+  st.markdown("<h1 style='text-align: center;'>Category A Sales Prediction</h1>", unsafe_allow_html=True)
+  st.write('Page ini berisi model untuk prediksi sales Category A, Product A1 & Product A2')
+
+  with st.form(key= 'form_a'):
+      st.markdown('##### **Forecast Sales Category A**')
+      input_a = st.number_input('Periode', min_value=0, max_value=90, value=5 ,step=1)
+      st.write('###### **Mean Absolute Error :** ', 3.69)
+      submitted_a = st.form_submit_button('Predict')
+
+  if submitted_a :
+      # Prediction
+      result_a = model_a.forecast(input_a)
+      result_a = pd.DataFrame(result_a)
+
+      # Visualisasi
+      fig = px.line(result_a, x=result_a.index, y=result_a.predicted_mean, title='Prediction Category A')
+      fig.update_layout(xaxis_title="Days", yaxis_title="Prediction")
+      fig.update_traces(line_color='red')
+      st.plotly_chart(fig)
+      st.write('**Prediction Category A :** ', result_a)
+
+  with st.form(key= 'form_a1'):
+      st.markdown('##### **Forecast Sales Product A1**')
+      input_a1 = st.number_input('Periode', min_value=0, max_value=90, value=5 ,step=1)
+      st.write('###### **Mean Absolute Error :** ', 7.4)
+      submitted_a1 = st.form_submit_button('Predict')
+
+  if submitted_a1 :
+      # Prediction
+      result_a1 = model_a1.forecast(input_a1)
+      result_a1 = pd.DataFrame(result_a1)
+
+      # Visualisasi
+      fig = px.line(result_a1, x=result_a1.index, y=result_a1.predicted_mean, title='Prediction Product A1')
+      fig.update_layout(xaxis_title="Days", yaxis_title="Prediction")
+      fig.update_traces(line_color='red')
+      st.plotly_chart(fig)
+      st.write('**Prediction Product A1 :** ', result_a1)
+
+  with st.form(key= 'form_a2'):
+      st.markdown('##### **Forecast Sales Product A2**')
+      input_a2 = st.number_input('Periode', min_value=0, max_value=90, value=5 ,step=1)
+      st.write('###### **Mean Absolute Error :** ', 1.73)
+      submitted_a2 = st.form_submit_button('Predict')
+
+  if submitted_a2 :
+      # Prediction
+      result_a2 = model_a2.forecast(input_a2)
+      result_a2 = pd.DataFrame(result_a2)
+
+      # Visualisasi
+      fig = px.line(result_a2, x=result_a2.index, y=result_a2.predicted_mean, title='Prediction Product A2')
+      fig.update_layout(xaxis_title="Days", yaxis_title="Prediction")
+      fig.update_traces(line_color='red')
+      st.plotly_chart(fig)
+      st.write('**Prediction Product A2 :** ', result_a2)
+
+
+if __name__ == '__main__':
+    run()
+      

prediction_b.py

@@ -0,0 +1,81 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import matplotlib.pyplot as plt
+import plotly.express as px
+
+# Load Model Kategori B
+with open('model_b.pkl', 'rb') as file_2:
+  model_b = pickle.load(file_2)
+
+# Load Model Produk B1
+with open('model_b1.pkl', 'rb') as file_5:
+  model_b1 = pickle.load(file_5)
+
+# Load Model Produk B2
+with open('model_b2.pkl', 'rb') as file_6:
+  model_b2 = pickle.load(file_6)
+
+def run() :
+    st.markdown("<h1 style='text-align: center;'>Category B Sales Prediction</h1>", unsafe_allow_html=True)
+    st.write('Page ini berisi model untuk prediksi sales Category B, Product B1 & Product B2')
+
+    with st.form(key= 'form_b'):
+        st.markdown('##### **Forecast Sales Category B**')
+        input_b = st.number_input('Periode', min_value=0, max_value=90, value=5 ,step=1)
+        st.write('###### **Mean Absolute Error :** ', 194.48)
+        submitted_b = st.form_submit_button('Predict')
+
+    if submitted_b :
+        # Prediction
+        result_b = model_b.forecast(input_b)
+        result_b = pd.DataFrame(result_b)
+
+        # Visualisasi
+        fig = px.line(result_b, x=result_b.index, y=result_b.predicted_mean, title='Prediction Category B')
+        fig.update_layout(xaxis_title="Days", yaxis_title="Prediction")
+        fig.update_traces(line_color='red')
+        st.plotly_chart(fig)
+        st.write('**Prediction Category B :** ', result_b)
+
+    with st.form(key= 'form_b1'):
+        st.markdown('##### **Forecast Sales Product B1**')
+        input_b1 = st.number_input('Periode', min_value=0, max_value=90, value=5 ,step=1)
+        st.write('###### **Mean Absolute Error :** ', 120.9)
+        submitted_b1 = st.form_submit_button('Predict')
+
+    if submitted_b1 :
+        # Prediction
+        result_b1 = model_b1.forecast(input_b1)
+        result_b1 = pd.DataFrame(result_b1, columns=['predicted_mean'])
+
+        # Visualisasi
+        fig = px.line(result_b1, x=result_b1.index, y= result_b1.predicted_mean, title='Prediction Product B1')
+        fig.update_layout(xaxis_title="Days", yaxis_title="Prediction")
+        fig.update_traces(line_color='red')
+        st.plotly_chart(fig)
+        st.write('**Prediction Product B1 :** ', result_b1)
+
+    with st.form(key= 'form_b2'):
+        st.markdown('##### **Forecast Sales Product B2**')
+        input_b2 = st.number_input('Periode', min_value=0, max_value=90, value=5 ,step=1)
+        st.write('###### **Mean Absolute Error :** ', 118.66)
+        submitted_b2 = st.form_submit_button('Predict')
+
+    if submitted_b2 :
+        # Prediction
+        result_b2 = model_b2.forecast(input_b2)
+        result_b2 = pd.DataFrame(result_b2, columns=['predicted_mean'])
+
+        # Visualisasi
+        fig = px.line(result_b2, x=result_b2.index, y=result_b2.predicted_mean, title='Prediction Product B2')
+        fig.update_layout(xaxis_title="Days", yaxis_title="Prediction")
+        fig.update_traces(line_color='red')
+        st.plotly_chart(fig)
+        st.write('**Prediction Product B2 :** ', result_b2)
+
+
+if __name__ == '__main__':
+    run()
+    

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+pandas
+seaborn
+matplotlib
+scikit-learn == 1.0.2
+numpy
+plotly