added ethereum price prediction project

Predict-Ethereum/.gitignore

@@ -0,0 +1,3 @@
+.env
+myenv/
+

Predict-Ethereum/EthereumPricePrediction/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for EthereumPricePrediction project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.0/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'EthereumPricePrediction.settings')
+
+application = get_asgi_application()

Predict-Ethereum/EthereumPricePrediction/settings.py

@@ -0,0 +1,83 @@
+"""
+Django settings for EthereumPricePrediction project.
+
+Generated by 'django-admin startproject' using Django 5.0.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.0/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/5.0/ref/settings/
+"""
+
+import os
+from pathlib import Path
+from decouple import config
+
+SECRET_KEY = config('SECRET_KEY')
+
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+
+
+# Application definition
+INSTALLED_APPS = [
+    'mainapp.app',
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+    'bootstrap5',
+]
+
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+    'whitenoise.middleware.WhiteNoiseMiddleware',  # Keep this for static files
+]
+
+ROOT_URLCONF = 'EthereumPricePrediction.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'EthereumPricePrediction.wsgi.application'
+
+
+
+# Static files (CSS, JavaScript, Images)
+STATIC_URL = '/static/'
+STATIC_ROOT = os.path.join(BASE_DIR, 'staticfiles')
+STATICFILES_STORAGE = 'whitenoise.storage.CompressedManifestStaticFilesStorage'
+
+# Media files
+MEDIA_URL = '/images/'
+MEDIA_ROOT = os.path.join(BASE_DIR, 'images')
+
+# Default primary key field type
+DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'

Predict-Ethereum/EthereumPricePrediction/urls.py

@@ -0,0 +1,25 @@
+"""
+URL configuration for EthereumPricePrediction project.
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/5.0/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  path('', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  path('', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.urls import include, path
+    2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
+"""
+from django.contrib import admin
+from django.urls import path,include
+from django.conf import settings
+from django.conf.urls.static import static
+
+urlpatterns = [
+    path('admin/', admin.site.urls),
+    path('', include('mainapp.urls',namespace='mainapp')),
+]+ static(settings.MEDIA_URL, document_root=settings.MEDIA_ROOT)

Predict-Ethereum/EthereumPricePrediction/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for EthereumPricePrediction project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.0/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'EthereumPricePrediction.settings')
+
+application = get_wsgi_application()

Predict-Ethereum/README.md

@@ -0,0 +1,15 @@
+# Ethereum Price Prediction
+
+## Project Overview
+This project predicts Ethereum prices using machine learning models, specifically Random Forest and Extra Trees. The model leverages data sourced from an API(coingecko.com) over a 365-day period.
+
+## Features
+- Predicts Ethereum price based on historical data.
+- Uses machine learning algorithms for accurate predictions.
+
+## Requirements
+- Python 3.9
+- Django
+- Pandas
+- NumPy
+- Scikit-learn

Predict-Ethereum/mainapp/admin.py

@@ -0,0 +1,3 @@
+from django.contrib import admin
+
+# Register your models here.

Predict-Ethereum/mainapp/app.py

@@ -0,0 +1,6 @@
+from django.apps import AppConfig
+
+
+class MainappConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    name = 'mainapp'

Predict-Ethereum/mainapp/models.py

@@ -0,0 +1,3 @@
+from django.db import models
+
+# Create your models here.

Predict-Ethereum/mainapp/prediction.py

@@ -0,0 +1,139 @@
+
+import pandas as pd
+import requests
+from datetime import datetime, timedelta
+from sklearn.ensemble import RandomForestRegressor, ExtraTreesRegressor
+from sklearn.preprocessing import StandardScaler  
+from sklearn.model_selection import GridSearchCV
+import os.path
+import pickle
+
+# Function to fetch historical Ethereum price data from CoinGecko API
+def fetch_ethereum_data():
+    # Make a request to the CoinGecko API to fetch historical Ethereum price data
+    response = requests.get('https://api.coingecko.com/api/v3/coins/ethereum/market_chart?vs_currency=usd&days=365')
+
+    # Check if the request was successful
+    if response.status_code == 200:
+        # Parse the response JSON data
+        ethereum_data = response.json()
+
+        # Extract relevant data from the response
+        prices = ethereum_data['prices']
+        ethereum_df = pd.DataFrame(prices, columns=['Timestamp', 'Price'])
+
+        # Convert timestamp to datetime
+        ethereum_df['Timestamp'] = pd.to_datetime(ethereum_df['Timestamp'], unit='ms')
+
+        return ethereum_df
+    else:
+        # If the request failed, return None
+        print("Error in API")
+        return None
+
+# Function to train the model
+def train_model(X, y):
+    # Feature scaling using StandardScaler
+    scaler = StandardScaler()
+    X_scaled = scaler.fit_transform(X)  # Scale the features
+
+    # Hyperparameter tuning for Random Forest
+    rf_param_grid = {'n_estimators': [100, 200, 300],
+                     'max_depth': [None, 10, 20, 30],
+                     'min_samples_split': [2, 5, 10]}
+    rf_grid_search = GridSearchCV(RandomForestRegressor(), rf_param_grid, cv=5)
+    rf_grid_search.fit(X_scaled, y)
+    best_rf_model = rf_grid_search.best_estimator_
+
+    # Hyperparameter tuning for Extra Trees
+    et_param_grid = {'n_estimators': [100, 200, 300],
+                     'max_depth': [None, 10, 20, 30],
+                     'min_samples_split': [2, 5, 10]}
+    et_grid_search = GridSearchCV(ExtraTreesRegressor(), et_param_grid, cv=5)
+    et_grid_search.fit(X_scaled, y)
+    best_et_model = et_grid_search.best_estimator_
+
+    return best_rf_model, best_et_model, scaler  # Return scaler for future scaling
+
+# Function to check if the model needs to be retrained
+def check_if_retrain_needed(ethereum_data):
+    # Check if the model file exists
+    if not os.path.exists("trained_model.pkl"):
+        return True
+
+    # Check the last modification time of the model file
+    last_modified_time = datetime.fromtimestamp(os.path.getmtime("trained_model.pkl"))
+
+    # Check if the last training time is more than a day ago
+    if datetime.now() - last_modified_time > timedelta(days=1):
+        return True
+    else:
+        return False
+
+# Load historical Ethereum price data from the CoinGecko API
+ethereum_data = fetch_ethereum_data()
+
+if ethereum_data is not None and check_if_retrain_needed(ethereum_data):
+
+    ethereum_data['Year'] = ethereum_data['Timestamp'].dt.year
+    ethereum_data['Month'] = ethereum_data['Timestamp'].dt.month
+    ethereum_data['Day'] = ethereum_data['Timestamp'].dt.day
+    ethereum_data['Weekday'] = ethereum_data['Timestamp'].dt.weekday
+
+    # Split data into features (X) and target variable (y)
+    X = ethereum_data[['Year', 'Month', 'Day', 'Weekday']]  
+    y = ethereum_data['Price']  
+
+    # Train the model
+    best_rf_model, best_et_model, scaler = train_model(X, y)
+
+    # Save the trained model and scaler
+    with open("trained_model.pkl", "wb") as f:
+        pickle.dump((best_rf_model, best_et_model, scaler), f)
+
+elif ethereum_data is not None and not check_if_retrain_needed(ethereum_data):
+    print("Model is already up to date, no need to retrain.")
+
+else:
+    print("Failed to fetch Ethereum data from the CoinGecko API.")
+
+# Load the pre-trained model and scaler
+if os.path.exists("trained_model.pkl"):
+    with open("trained_model.pkl", "rb") as f:
+        best_rf_model, best_et_model, scaler = pickle.load(f)
+
+# Random Forest
+def predict_prices_for_future_random_forest(date):
+    # Preprocess input date provided by the user
+    date = pd.to_datetime(date)
+    year = date.year
+    month = date.month
+    day = date.day
+    weekday = date.weekday()
+
+    # Feature scaling for prediction using the stored scaler
+    scaled_features_for_date = scaler.transform([[year, month, day, weekday]])
+
+    # Make prediction using the best Random Forest model
+    predicted_price = best_rf_model.predict(scaled_features_for_date)[0]
+
+    # Return tuple of predicted price and default value for predicted high and low
+    return predicted_price, predicted_price + 100, predicted_price - 200
+
+    #Extra Trees
+
+def predict_prices_for_future_extra_trees(date):
+
+    date = pd.to_datetime(date)
+    year = date.year
+    month = date.month
+    day = date.day
+    weekday = date.weekday()
+
+
+    scaled_features_for_date = scaler.transform([[year, month, day, weekday]])
+
+
+    predicted_price = best_et_model.predict(scaled_features_for_date)[0]
+
+    return predicted_price, predicted_price + 100, predicted_price - 200