Speaker 1: Hey guys, again I have come with another project Stock Price Prediction Using Machine Learning Algorithm. So in this tutorial we are going to implement a stock price prediction model using a machine learning technique. So stock price prediction model as the name suggests it predicts the price of the stock based on the different parameters like high, open, low, close etc. So I have trained this model using a multilinear regression model, it's a simple linear regression model and it gave me a 5% RMSE, RMSE stands for Root Mean Squared Error. So let's start the project. So first of all import all the required libraries like pandas, numpy, matplotlib, seaborn for data visualization and EDA. Then load a apple data set using a read underscore csv method of pandas and display the top 5 rows of the apple data set. So this data set is taken from NASDAQ apple included company. Next step is to perform the EDA, EDA stands for Exploratory Data Analysis. So in EDA firstly check that there are null values present or not. So you can see that there is no null values present in the data set. Now check the shape of the data set, here 1090 rows are present and 13 columns. Then check the correlation of the data set. So using the core method you can see the correlation but in this it's difficult to understand the correlation. So with the help of the heatmap function of the seaborn we visualize the correlation of our data set. So you can clearly visualize the correlation using the heatmap function. Like these 1111 are highly correlated, just ignore this diagonal line and see other values. Like here you can see there is a negative correlation, there is a positive correlation. Now visualize each and every feature using the hist method. Now create a new feature using the existing feature. You can create the new features with the help of the domain knowledge. If you have domain knowledge so you can create a new feature. So PCT stands for Percentage. I have created two new features with the help of the domain knowledge. Then display the top 5 rows of the data set. So now the next step is to prepare the data set. I took only 5 features to train the ML model. So now display the top 5 rows of the data set which contains only 5 features. Now again check that there are null values present or not. Now divide the data set into the independent and dependent features. So with the help of all the independent features our model predicts the dependent feature or you can say the target feature or output feature. So X contains all the independent feature and Y contains our dependent feature. Dependent feature is our adjacent close. Now display the top 5 rows of the X data set and display the top 5 rows of the Y data set. These all are our independent feature and this is our dependent feature. Now the next step is to split the data set into the training and testing. So import TrainTestSplit class from the sklearn. So split the data set into the training and testing using the TrainTestSplit method which takes some parameter like X, Y, TestSite, RandomState which returns 4 data set XTrain, XTest, YTrain, YTest. XTrain contains independent features for training and YTrain contains dependent feature for training and same as XTest and YTest. XTest contains all the independent features for the testing and YTest contains dependent feature for test. Now import our model LinearRegression and import a normalization technique StandardScalar. StandardScalar basically used to convert the values in a particular range. Now apply the normalization technique on XTrain and XTest. Now define our LinearRegression model and train the model using the training data set. Now its time to evaluate the model. So test the model using the test data set like you can see here these all values are predicted values and these all values are YTest contains all the actual output. These predicted output, these actual output. Now create a new data frame to compare the values of the actual output and the predicted output like you can see here the actual output is 22.87 and the predicted output is 22.03. Its near. Now its time to evaluate the model like how it is performing. So import mean absolute error and mean squared error. So you can see here mean absolute error is 4.27, mean squared error is 27.96 and root mean square is 5%. So like you can see here its performing very well on our data set. Model is trained perfectly. Its not overfitting or underfitting. So thank you guys. I hope you like the tutorial. If you like the tutorial please like, share and comment. Thank you guys. So if you are interested in data science, machine learning, deep learning, NLP, Python, class, project or tutorial so you can follow my this blog datascience2000.in. I upload here different different project tutorials related to data science, machine learning, deep learning, NLP, Python, class, Django. So just visit this blog and the source code and complete explanation of the stock price prediction you will get here. So I will provide the link in the description box. Thank you guys. Thank you. We will meet you in the next project.