T06 – Missing out on beliefs system Insight in Tamil how to Tool learning course free ( Statistics Technology )

T06 - Missing values strategy Intuition in Tamil - Machine learning course free ( Data Science )

*For the playlist , please click the below Link:

*Please click the following link to download the dataset: https://drive.google.com/file/d/10DbrdE0RTG8KMkdiOPu-7r1cgBOfhcyi/view?usp=sharing

*Visit Our website : https://datasciencealive.wordpress.com/machine-learning/

*In this session we will look into strategy used in Handling missing values on the data preprocessing techniques ( Tamil ) using pandas in python .

We will use the following strategy for handling the missing values
1. Mean = Average
2.Median = Middle value
3.Mode ( categorical data and continues values) = Most Frequent values

In machine learning ( Tamil ) most of the time will be spend on data preprocessing , data mining and feature extraction . Hence please listen to this topic more carefully .

*This is a Data science course ( Tamil ). This is a full fledge course for free and we will cove all the main topics on the machine learning algorithm. This course is specifically designed to address all the queries from beginners to expert . Artificial intelligence ( AI ) is a bigger umbrella ,In that Machine learning ( ML ) and Deep Learning ( DL ) are part of Artificial Intelligence.

*In this video we will have an overview on the topics that will be covered. On high level it will be

*Data Preprocessing
*Supervised Learning – Algorithm
*Classification
*Regression
*Association
*Unsupervised learning – Algorithm
*Clustering
*Dimensionality Reduction (PCA)
*Semi -Supervised learning
*Re- Enforcement learning
*Best approach for Model selection
*Intro to Deep Learning

The above topics will be covered in-detail on the upcoming session which you can find it in the below playlist .

*For the playlist , please click the below Link:

#Data_science_tamil #Missing_values #Machine_learning_Python_tamil

Link to the code: https://github.com/mGalarnyk/Python_Tutorials/blob/master/Time_Series/Part1_Time_Series_Data_BasicPlotting.ipynb

Viewing Pandas DataFrame, Adding Columns in Pandas, Plotting Two Pandas Columns, Sampling Using Pandas, Rolling mean in Pandas (Smoothing), Subplots, Plotting against Date (numpy.datetime), Filtering DataFrame in Pandas, Simple Joins, and Linear Regression.

This tutorial is mostly focused on manipulating time series data in the Pandas Python Library.

20 Antworten auf „T06 – Missing out on beliefs system Insight in Tamil how to Tool learning course free ( Statistics Technology )“

  1. How to handle the data if the start time and end time is already given for each row of the data? There can be more then one time periods of different rows between one time period of an row if we take an example.

  2. Hi Mike I can't even get started with this tutorial because Google is blocking the get URL function in the code. Is there a way to start with a csv file of Google stock data?

  3. Thank you for quality tutorials. It's such a nice thing to have rolling statistics and actual data on the same plot and have datetime x axis. Is there a way to have regression line with rolling mean and actual data on the same plot and also have datetime x axis?

  4. Hello Michael. First of all congratulations for the channel I always follow and that is a good thing. I would ask if possible to do a tutorial on periodograms in particular using Gauss and Lomb-Scargle transformations under the pandas module approach.

  5. Michael
    Many thanks for the video. Brief as it may be, it is perfect for someone like me. I just started learning Python. This is my first crack at matplotlib and sklearn.
    Also, can't thank you enough for recording in 4K. It was so much easier reading the code. There are some good videos on this site covering important topics. But so many of them are of such low resolution, I can barely follow the blurry text in those videos.
    Cheers

Schreibe einen Kommentar

Deine E-Mail-Adresse wird nicht veröffentlicht. Erforderliche Felder sind mit * markiert.