Upload 4 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
+rtv.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,127 @@
+# import libraries
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+from sklearn.ensemble import RandomForestRegressor
+import matplotlib.pyplot as plt
+
+
+df = pd.read_csv("rtv.csv", low_memory=False)
+
+# load model from pickle file
+with open("rf.pkl", "rb") as f:
+    rf = pickle.load(f)
+    
+st.set_page_config(
+    page_title = 'Real-Time Data Science Dashboard',
+    page_icon = '✅',
+    layout = 'wide'
+)
+
+# create sidebar title
+st.title("Raising the :green[Village] :desert:")
+st.image("https://ngosjob.b-cdn.net/wp-content/uploads/2023/03/Raising-The-Village.png")
+
+
+
+# creating a single-element container.
+placeholder = st.empty()
+
+duration = df['duration'].mean()
+
+mean = pd.to_numeric(df['HH Income (UGX)'], errors='coerce').mean()
+
+maxi = pd.to_numeric(df['HH Income (UGX)'], errors='coerce').max()
+
+with placeholder.container():
+    # create three columns
+    kpi1, kpi2, kpi3 = st.columns(3)
+
+    # fill in those three columns with respective metrics or KPIs 
+    kpi1.metric(label="Average Income ⏳", value=round(mean))
+    kpi2.metric(label="Mean Time(minutes) 💍", value= int(duration))
+    kpi3.metric(label="Max income＄", value= f"$ {round(maxi,2)} ")
+    
+    
+# create title
+st.title("Income Prediction")
+
+# create input fields for each feature
+inputs = []
+X_columns = ['Season 2 Agriculture Value (Ugx)',
+ 'Casual Labour (Ugx)',
+ 'Season 1 Agriculture Value (Ugx)',
+ 'Perenial Crops Income (Ugx)',
+ 'Personal Business & Self Employment (Ugx)',
+ 'Agriculture Income (UGX) ',
+ 'Perennial Agriculture Value (Ugx)',
+ 'HH Income + Consumption + Residues (UGX)']
+for col in X_columns:
+    value = st.number_input(f"Enter value for {col}", value=0.0)
+    inputs.append(value)
+
+# create button for prediction
+predict = st.button("Predict Income")
+
+if predict:
+    # convert inputs to numpy array and reshape to match model input shape
+    inputs = np.array(inputs).reshape(1, -1)
+    # make prediction using loaded model
+    y_pred = rf.predict(inputs)
+    # display prediction result
+    st.write(f"The predicted income value is {y_pred[0]:.2f}")
+
+st.markdown("============================================================================================================================")
+
+# make prediction and display result if button is clicked and data is uploaded
+# display file upload option
+st.title("Get predictions of the whole dataset")
+st.write("Upload your csv or excel file here:")
+st.write("The dashboard supports only csv files at the moment")
+uploaded_file = st.file_uploader("Choose a file", type=["csv", "xlsx"])
+
+def preproc(df):
+    df = df[['Season 2 Agriculture Value (Ugx)',
+         'Casual Labour (Ugx)',
+         'Season 1 Agriculture Value (Ugx)',
+         'Perenial Crops Income (Ugx)',
+         'Personal Business & Self Employment (Ugx)',
+         'Agriculture Income (UGX) ',
+         'Perennial Agriculture Value (Ugx)',
+         'HH Income + Consumption + Residues (UGX)']]
+    df.fillna(df.mean(), inplace=True)
+    return df
+
+# load and display data if uploaded
+if uploaded_file is not None:
+    if uploaded_file.type == "text/csv":
+        df = pd.read_csv(uploaded_file)
+    elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet":
+        df = pd.read_excel(uploaded_file)
+    X_new = preproc(df)
+else:
+    st.write("No file uploaded yet.")
+
+# create button for prediction
+predict = st.button("Predict")
+
+# make prediction and display result if button is clicked and data is uploaded
+if uploaded_file is not None and predict:
+    # make prediction using loaded model
+    y_pred = rf.predict(X_new)
+    # display prediction result as dataframe
+    df["prediction"] = y_pred.round(2)
+    st.dataframe(df[["Surveyor_Name", "prediction"]])
+
+job_filter = st.selectbox("Select the Quartile", pd.unique(df['Quartile']))
+
+
+
+# dataframe filter 
+
+df1 = df[df['Quartile']==job_filter]
+
+
+
+st.dataframe(df1)

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+pandas 
+numpy 
+pickle

rf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c8e318af92fe4e3af97ff8b22dfa69a031cfb8303f1ebf7999fe6074eca640
+size 36759795

rtv.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f9eae8cadea44db9b35480b0d879bc37a5b3791d854b19119a20eec0c81f5c
+size 11814212