R Squared Machine Learning Metrics from Scratch in Python:
import numpy as np
def r2_squared(y_test,y_pred):
y_mean=np.mean(y_test)
tss=np.sum((y_test-y_mean)**2)
rss=np.sum((y_test-y_pred)**2)
rt=1-(rss/tss)
return rt
print(r2_squared(y_test,y_pred))
R-squared (R²) Metrics to Evaluate the Performance of Machine Learning Models in Python:
Follow the Instructions from the above Video then go for the Code Input:
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
import pandas as pd
from fyers_apiv3 import fyersModel
from datetime import datetime,timedelta
import matplotlib.pyplot as plt
client_id=open('C:/Users/VIKASH/Desktop/fyersv3/app_id.txt','r').read()
token=open('C:/Users/VIKASH/Desktop/fyersv3/access_token.txt','r').read().strip()
fyers=fyersModel.FyersModel(client_id=client_id,token=token,log_path='C:/Users/VIKASH/Desktop/fyersv3')
days=1
symbol='NSE:NIFTYBANK-INDEX'
interval='1'
now=datetime.now()
from_date=now-timedelta(days=days)
from_date=datetime.strftime(from_date,'%Y-%m-%d')
to_date=datetime.strftime(now,'%Y-%m-%d')
print(now,symbol,interval,from_date,to_date)
def historical_data(symbol,interval,from_date,to_date):
data={'symbol':symbol,
'resolution':interval,
'date_format':'1',
'range_from':from_date,
'range_to':to_date,
'cont_flag':'1'
}
response=pd.DataFrame(fyers.history(data=data)['candles'],columns=['date','open','high','low','close','volume'])
return response
df=historical_data(symbol,interval,from_date,to_date)
#feature and target
X=df[['open']]
y=df['close']
#test and train
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)
#Train Model
model=LinearRegression()
model.fit(X_train,y_train)
#predict
y_pred=model.predict(X_test)
print(r2_score(y_test,y_pred))
print(X_test.iloc[-1],y_test.iloc[-1],y_pred[-1])
plt.figure(figsize=(10,5))
plt.scatter(X_test,y_test,color='blue',label='Actual')
plt.plot(X_test,y_pred,color='red',label='Predicted')
plt.xlabel('open')
plt.ylabel('close')
plt.title('Actual V/s Predicted')
plt.legend()
plt.savefig('metrics.png')
plt.show()
Predict Stock Close Price Based on Open Price Using Machine Learning in Python:
Predict Stock Prices Using Machine Learning with ChatGPT in Python Part-2:
Predict Stock Prices Using Machine Learning with ChatGPT in Python Part-3:
Follow the Instructions from the above Video then go for the Code Input:
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import pandas as pd
from fyers_apiv3 import fyersModel
from datetime import datetime,timedelta
import matplotlib.pyplot as plt
client_id=open('C:/Users/VIKASH/Desktop/fyersv3/app_id.txt','r').read()
token=open('C:/Users/VIKASH/Desktop/fyersv3/access_token.txt','r').read().strip()
fyers=fyersModel.FyersModel(client_id=client_id,token=token,log_path='C:/Users/VIKASH/Desktop/fyersv3')
days=1
symbol='NSE:NIFTY50-INDEX'
interval='1'
now=datetime.now()
from_date=now-timedelta(days=days)
from_date=datetime.strftime(from_date,'%Y-%m-%d')
to_date=datetime.strftime(now,'%Y-%m-%d')
print(now,symbol,interval,from_date,to_date)
def historical_data(symbol,interval,from_date,to_date):
data={'symbol':symbol,
'resolution':interval,
'date_format':'1',
'range_from':from_date,
'range_to':to_date,
'cont_flag':'1'
}
response=pd.DataFrame(fyers.history(data=data)['candles'],columns=['date','open','high','low','close','volume'])
return response
df=historical_data(symbol,interval,from_date,to_date)
#set feature and target
X=df[['open']]
y=df['close']
#split data for train and test
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)
#Train the Model
model=LinearRegression()
model.fit(X_train,y_train)
#Predict
y_pred=model.predict(X_test)
#Evaluate
mse=mean_squared_error(y_test,y_pred)
print(mse)
new_open_price=X_test
predicted=pd.DataFrame(model.predict(new_open_price))
predicted.plot()
plt.show()
Create a FlowChart Diagram using Graphviz in Python:
Follow the Instructions from the above Video then go for the Code Input:
import graphviz
dot= """
digraph MachineLearning{
node[shape=box,style=filled,fillcolor=white];
Start[shape=square];
End[shape=square];
Start -> "Data Collection" [label="Collect Stock Prices Data"];
"Data Collection" -> "Data Preprocessing" [label="Clean and Normalize Data"];
"Data Preprocessing" -> "Model Training" [label="Train Linear regression Model"];
"Model Training" -> "Model Evaluation" [label="Evaluate Model"];
"Model Evaluation" -> "Prediction" [label="Predicting Future Stock Price"];
"Prediction" ->End;
}
"""
graph=graphviz.Source(dot)
graph.render(filename='ML_FLOWCHART',format='png')
Predict Stock Prices using Machine Learning with ChatGPT in Python:
What is ChatGPT?:
ChatGPT is an AI language model developed by OpenAI. It's designed to generate human-like text based on the input it receives. It's trained on a large dataset of diverse text from the internet, allowing it to understand and generate responses on a wide range of topics. ChatGPT can be used for various purposes, including answering questions, generating text, assisting with writing tasks, and engaging in conversation. It's part of a broader effort to develop artificial intelligence that can understand and communicate with humans in natural language.
Machine Learning:
Machine learning is a subset of artificial intelligence (AI) that focuses on enabling computers to learn from data and improve over time without being explicitly programmed to do so. In essence, machine learning algorithms allow computers to recognize patterns in data and make predictions or decisions based on those patterns. There are several types of machine learning algorithms, including:
1. **Supervised learning**: In supervised learning, the algorithm is trained on a labeled dataset, meaning that each input is associated with a corresponding output. The goal is for the algorithm to learn a mapping from inputs to outputs so that it can make predictions on new, unseen data.
2. **Unsupervised learning**: Unsupervised learning involves training algorithms on unlabeled data, where the algorithm must discover hidden patterns or structures within the data on its own. Clustering and dimensionality reduction are common tasks in unsupervised learning.3. **Reinforcement learning**: In reinforcement learning, an agent learns to make decisions by interacting with an environment. The agent receives feedback in the form of rewards or penalties based on its actions, and its goal is to learn the optimal policy for maximizing cumulative rewards over time.
Machine learning has numerous applications across various domains, including image and speech recognition, natural language processing, recommendation systems, medical diagnosis, financial forecasting, and more. It forms the basis of many cutting-edge technologies and plays a crucial role in advancing AI capabilities.Machine Learning in Python:
Machine learning in Python is highly popular due to the availability of powerful libraries and frameworks specifically designed for machine learning tasks. Some of the most commonly used libraries for machine learning in Python include:
1. **scikit-learn**: This is one of the most popular machine learning libraries in Python. It provides simple and efficient tools for data mining and data analysis. Scikit-learn includes a wide range of algorithms for classification, regression, clustering, dimensionality reduction, and more.
2. **TensorFlow**: Developed by Google Brain, TensorFlow is an open-source machine learning framework that provides tools for building and training neural networks. It offers both high-level APIs (such as Keras) for easy model building and low-level APIs for more flexibility.3. **PyTorch**: Developed by Facebook's AI Research lab, PyTorch is another popular open-source machine learning framework. It's known for its dynamic computation graph feature, which allows for more flexible and intuitive model development compared to static graph frameworks like TensorFlow.
4. **NumPy**: While not strictly a machine learning library, NumPy is a fundamental package for scientific computing in Python. It provides support for multi-dimensional arrays and mathematical functions, making it essential for handling data in machine learning tasks.5. **Pandas**: Pandas is a powerful library for data manipulation and analysis in Python. It provides data structures like DataFrame, which are well-suited for handling structured data, such as CSV files or database tables, commonly used in machine learning.
6. **Matplotlib** and **Seaborn**: These libraries are used for data visualization in Python. They allow you to create various types of plots and charts to explore and visualize your data before and after training your machine learning models. To get started with machine learning in Python, you would typically install these libraries using package managers like pip or conda and then use their APIs to load, preprocess, train, and evaluate machine learning models on your data. There are also numerous tutorials, courses, and resources available online to help you learn and apply machine learning techniques using Python./h3>Predict Stock Prices Based on Yahoo Fnance OHLCV Data using Machine Learning in Python:
CMD>>pip installation>> : pip install yfinance and pip install scikit-learn
Predicting StockPrices based on OHLCV (Open, High, Low, Close, Volume) data from Yahoo Finance using machine learning in Python is a common task in quantitative finance and machine learning. Here's a high-level overview of how you can approach this task:
1. **Data Collection**: Obtain historical OHLCV data for the stock(s) you want to predict. You can use libraries like `yfinance` in Python to fetch this data directly from Yahoo Finance.
2. **Data Preprocessing**: Once you have the data, preprocess it by handling missing values, scaling the features, and splitting it into training and testing sets. You may also want to engineer additional features such as technical indicators (e.g., moving averages, RSI) or lagged variables.3. **Feature Selection/Engineering**: Select relevant features for your prediction model. This could include not only OHLCV data but also any additional features you engineered in the preprocessing step.
4. **Model Selection**: Choose an appropriate machine learning model for your prediction task. Common choices for stock price prediction include linear regression, support vector machines (SVM), decision trees, random forests, gradient boosting, and neural networks.5. **Training**: Train your selected model on the training data. You may need to tune hyperparameters using techniques like cross-validation to optimize model performance.
6. **Evaluation**: Evaluate the trained model on the testing data using appropriate evaluation metrics, such as mean squared error (MSE), mean absolute error (MAE), or root mean squared error (RMSE).7. **Prediction**: Once the model is trained and evaluated, use it to make predictions on new, unseen data.
Here's a simplified example using linear regression in Python:
import yfinance as yf
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
# Fetch historical data from Yahoo Finance
data = yf.download('AAPL', start='2020-01-01', end='2021-01-01')
# Preprocess data
# (You may need to handle missing values, scale features, engineer additional features, etc.)
# Split data into features (X) and target (y)
X = data[['Open', 'High', 'Low', 'Close', 'Volume']]
y = data['Close']
# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Train a linear regression model
model = LinearRegression()
model.fit(X_train, y_train)
# Evaluate the model
y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print(f"Mean Squared Error: {mse}")
