init: Frontend: Streamlit + Backend + ML

app.py

@@ -0,0 +1,131 @@
+# app.py
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import plotly.express as px
+from PIL import Image
+import json
+import csv
+import streamlit as st
+from sklearn.preprocessing import LabelEncoder
+from sklearn.ensemble import RandomForestClassifier
+from geopy.distance import geodesic
+import osmnx as ox
+from sklearn.linear_model import LogisticRegression
+from sklearn.svm import SVC
+from sklearn.tree import DecisionTreeClassifier
+
+# Read data
+pd.set_option('display.max_columns', None)
+df = pd.read_json("./Tourist_related.json")
+
+# Convert data to CSV
+with open('./data.csv', 'w') as data_file:
+    csv_writer = csv.writer(data_file)
+    csv_writer.writerow(df.columns)
+    csv_writer.writerows(df.values)
+
+# Read CSV data
+read_dat = pd.read_csv('./data.csv', on_bad_lines='skip')
+
+# Function for data quality test
+def data_quality_test():
+    check_na = read_dat.isnull().sum()
+    for features, count in check_na.items():
+        print(f'{features}: {count}')
+
+# Function for correlation analysis
+def correlation_analysis():
+    plt.figure(figsize=(12, 6))
+    sns.heatmap(df.corr(), annot=True)
+    st.pyplot()
+
+# Geo Plot Visualization Function
+def geo_plot_visualization():
+    df['lat'] = df['location'].apply(lambda x: x.get('lat', None))
+    df['lng'] = df['location'].apply(lambda x: x.get('lng', None))
+
+    color_scale = [(0, 'orange'), (1, 'red')]
+
+    fig = px.scatter_mapbox(df,
+                            lat="lat",
+                            lon="lng",
+                            color_continuous_scale=color_scale,
+                            zoom=8,
+                            height=800,
+                            width=800)
+
+    fig.update_layout(mapbox_style="open-street-map")
+    fig.update_layout(margin={"r": 0, "t": 0, "l": 0, "b": 0})
+
+    st.plotly_chart(fig)
+
+# Function for image category recognition
+def predict_image_category(image_url):
+    # Replace this part with your image classification logic
+    # For example, you can use a pre-trained deep learning model
+    # Here, I'm using a placeholder
+    categories = ['Category A', 'Category B', 'Category C']
+    prediction = np.random.choice(categories)
+    return prediction
+
+# Random Forest Classifier
+def train_random_forest():
+    # Assuming 'target' is the target variable
+    X = df.drop('target', axis=1)
+    y = df['target']
+
+    # Assuming 'categorical_columns' is a list of categorical columns
+    le = LabelEncoder()
+    for col in categorical_columns:
+        X[col] = le.fit_transform(X[col])
+
+    # Create and train the random forest classifier
+    rf_classifier = RandomForestClassifier()
+    rf_classifier.fit(X, y)
+
+    return rf_classifier
+
+# Streamlit UI
+def main():
+    st.title("Tourist Analysis App")
+
+    # Sidebar
+    st.sidebar.subheader("Navigation")
+    page = st.sidebar.radio("Go to", ("Home", "Data Quality Test", "Correlation Analysis", "Geo Plot Visualization", "Image Upload"))
+
+    if page == "Home":
+        st.write("# Welcome to Tourist Analysis App")
+        st.write("Use the sidebar to navigate to different sections.")
+
+    elif page == "Data Quality Test":
+        st.write("# Data Quality Test")
+        data_quality_test()
+
+    elif page == "Correlation Analysis":
+        st.write("# Correlation Analysis")
+        correlation_analysis()
+
+    elif page == "Geo Plot Visualization":
+        st.write("# Geo Plot Visualization")
+        geo_plot_visualization()
+
+    elif page == "Image Upload":
+        st.write("# Image Upload")
+        uploaded_file = st.file_uploader("Choose an image...", type="jpg")
+
+        if uploaded_file is not None:
+            image = Image.open(uploaded_file)
+            st.image(image, caption="Uploaded Image.", use_column_width=True)
+            st.write("")
+            st.write("Classifying...")
+
+            # Predict the image category
+            prediction = predict_image_category(image)
+
+            st.write("Prediction:", prediction)
+
+if __name__ == "__main__":
+    main()

model_card.md

@@ -0,0 +1,23 @@
+---
+tags:
+  - machine-learning
+  - data-visualization
+  - geospatial
+---
+
+# CIDM TEAM A Location Recommender
+
+This script uses machine learning to recommend locations based on swiped images and visualizes them on a map.
+
+## Usage
+
+1. Open the Jupyter Notebook in the [Hugging Face Spaces](https://huggingface.co/spaces) environment.
+2. Execute the cells one by one.
+3. View the generated map to see recommended locations and the closest one.
+
+## Dependencies
+
+- pandas
+- scikit-learn
+- plotly
+- geopy

requirements.txt

@@ -0,0 +1,15 @@
+pandas
+scikit-learn
+plotly
+geopy
+PIL
+json
+csv
+io
+requests
+flask
+osmnx
+numpy
+seaborn
+matplotlib
+streamlit

result.html

@@ -0,0 +1,15 @@
+<!-- templates/result.html -->
+
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Image Category Recognition Result</title>
+</head>
+<body>
+    <h1>Image Category Recognition Result</h1>
+    <p>Prediction: {{ prediction }}</p>
+</body>
+</html>