gold_price_prediction_using_ml.py

# -*- coding: utf-8 -*-
"""Gold Price Prediction Using ML.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1E8nMsbWy72jW9107hmKE3ert2xd9DEC2

**Importing the Libraries**
"""

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn import metrics

"""**Data Collection and Processing **

"""

gold_data = pd.read_csv('/content/gld_price_data.csv')

gold_data.head()

gold_data.tail()

gold_data.shape

gold_data.info()

gold_data.isnull().sum()

gold_data.describe()

"""**Checking Correlation**"""

correlation = gold_data.corr()

plt.figure(figsize = (8,8))
sns.heatmap(correlation, cbar=True, square=True, fmt='.1f',annot=True, annot_kws={'size':8}, cmap='Blues')

print(correlation['GLD'])

sns.distplot(gold_data['GLD'],color='green')

"""**Splitting the Features and Target**"""

x = gold_data.drop(['Date','GLD'],axis=1)
y = gold_data['GLD']

x

y

"""**Splitting into Training data and Test Data**"""

X_train,X_test,Y_train,Y_test = train_test_split(x,y,test_size=0.2,random_state=2)

"""**Model Training: Random Forest Regressor**"""

regressor = RandomForestRegressor(n_estimators=100)

regressor.fit(X_train,Y_train)

"""**Model Evaluation**"""

test_data_prediction = regressor.predict(X_test)

print(test_data_prediction)

error_score = metrics.r2_score(Y_test, test_data_prediction)
print('R squared error :', error_score)

"""**Compare the Actual Values and Predicted Values**"""

Y_test = list(Y_test)

plt.plot(Y_test, color ='blue', label='Actual Value')
plt.plot(test_data_prediction, color='green', label='predicted value')
plt.title('actual vs predicted')
plt.xlabel('no. of values')
plt.ylabel('gld prices')
plt.legend()
plt.show()