Create app.py

app.py

@@ -0,0 +1,129 @@
+import streamlit as st
+import pandas as pd
+import joblib
+
+from sklearn import preprocessing
+
+
+
+st.sidebar.header('User Input Parameters')
+
+def user_input_features():
+    fligh_number = st.number_input("Insert a FlightNumber")
+    payload_mass = st.sidebar.slider('Payload Mass', 350, 30000, 1000)
+
+    flights = st.sidebar.slider('Flights', 1, 6, 3)
+
+    block = st.sidebar.slider('Block', 1,5,1 )
+    orbit = st.sidebar.selectbox('Orbit',('LEO', 'ISS', 'PO', 'GTO', 'ES-L1', 'SSO', 'HEO', 'MEO', 'VLEO',
+       'SO', 'GEO'))
+
+    reused_count = st.number_input('Insert a ReusedCount')
+    
+    launch_site = st.sidebar.selectbox('LaunchSite',('CCAFS SLC 40', 'VAFB SLC 4E', 'KSC LC 39A'))
+    
+    LandingPad = st.sidebar.selectbox('LandingPad',('5e9e3032383ecb761634e7cb', '5e9e3032383ecb6bb234e7ca',
+       '5e9e3032383ecb267a34e7c7', '5e9e3033383ecbb9e534e7cc',
+       '5e9e3032383ecb554034e7c9'))
+
+    serial = st.sidebar.selectbox('Serial',('B0003', 'B0005', 'B0007', 'B1003', 'B1004', 'B1005', 'B1006',
+       'B1007', 'B1008', 'B1011', 'B1010', 'B1012', 'B1013', 'B1015',
+       'B1016', 'B1018', 'B1019', 'B1017', 'B1020', 'B1021', 'B1022',
+       'B1023', 'B1025', 'B1026', 'B1028', 'B1029', 'B1031', 'B1030',
+       'B1032', 'B1034', 'B1035', 'B1036', 'B1037', 'B1039', 'B1038',
+       'B1040', 'B1041', 'B1042', 'B1043', 'B1044', 'B1045', 'B1046',
+       'B1047', 'B1048', 'B1049', 'B1050', 'B1054', 'B1051', 'B1056',
+       'B1059', 'B1058', 'B1060', 'B1062'))
+
+    gridfins = st.sidebar.selectbox('GridFins', (False, True))
+
+    reused = st.sidebar.selectbox('Reused', (False, True))
+
+    legs = st.sidebar.selectbox('Legs', (False, True))
+
+    
+    data = {'FlightNumber' : fligh_number ,
+        'PayloadMass': payload_mass,
+            'flights' : flights,
+            'block' : block ,
+            'ReusedCount' : reused_count , 
+            'Orbit': orbit,
+            'LaunchSite' : launch_site ,
+            'LandingPad' : LandingPad ,
+            'Serial' : serial ,
+            'GridFins' : gridfins ,
+            'Reused' : reused ,
+            'Legs' : legs
+            }
+    
+    features = pd.DataFrame(data, index=[0])
+    return features
+
+df = user_input_features()
+
+data = pd.read_csv('dataset_part_2.csv')
+
+
+orbit = pd.get_dummies(data['Orbit'], prefix="Orbit")
+launch_site = pd.get_dummies(data['LaunchSite'], prefix="LaunchSite")
+landing_pad = pd.get_dummies(data['LandingPad'], prefix="LandingPad")
+serial = pd.get_dummies(data['Serial'],prefix='Serial')
+gridfin = pd.get_dummies(data['GridFins'],prefix= 'GridFins')
+reused = pd.get_dummies(data['Reused'], prefix= 'Reused')
+legs = pd.get_dummies(data['Legs'],prefix= 'Legs')
+
+df.drop(['Orbit', 'LaunchSite', 'LandingPad','Serial','GridFins','Reused','Legs'], axis=1, inplace=True)
+
+#Concatenate the one-hot-encoded columns with the original DataFrame
+df = pd.concat([df,orbit, launch_site, landing_pad,serial,gridfin,reused,legs], axis=1)
+
+x_input = pd.DataFrame(df.iloc[0])
+x_input = x_input.transpose()
+
+
+transform = preprocessing.StandardScaler()
+X = transform.fit_transform(x_input)
+X
+print(X)
+st.write(X)
+
+
+# # Load the CSV file (replace with your file path or URL)
+# url = 'https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBM-DS0321EN-SkillsNetwork/datasets/dataset_part_3.csv'
+# df = pd.read_csv(url)
+
+# Load the pickle model (replace with your model path)
+model_path = 'decision_tree.joblib'
+# with open(model_path, 'rb') as file:
+#     model = pickle.load(file)
+model = joblib.load(model_path)
+
+st.write('Model is loaded successfully')
+
+pred = model.predict(x_input_sc)
+
+st.title("SpaceX Stage 1 Failed Predictor")
+
+
+# # Display the DataFrame
+# st.write("Data Preview")
+# st.dataframe(df.head())
+
+# # Select parameters from the header
+# st.write("Select Parameters for Prediction")
+# parameters = st.multiselect("Select columns to use for prediction", options=df.columns)
+
+# # Input values for the selected parameters
+# input_data = {}
+# for param in parameters:
+#     input_data[param] = st.number_input(f"Input value for {param}", value=0.0)
+
+# # Convert input data to DataFrame
+# input_df = pd.DataFrame([input_data])
+
+# # Prediction
+if st.button("Submit"):
+    classes = ['Failed','Success']
+    prediction = model.predict(x_input_sc)
+    st.write(f"Prediction: {prediction[0]}")
+