Master Python Data Analysis and Modelling Essentials

This lecture talks about how to install Anaconda Python and setup Anaconda prompt. After this lecture, you can install Anaconda Python on your system and pin Anaconda prompt on taskbar for use conveniently.

This lecture introduces the required pakcages. After this lecture, you will understand the difference between Python Modules, Packages and Libraries, and be clear what the packages are about.

This lecture show how to install the required packages. After this lecture, you will be able to install the basic required packages for data analysis and modelling.

This lecture shows how to create working directory and its subfolders and start jupyter notebook with Anaconda Prompt, as well as create a Jupyter notebook. After this lecture, you will be able to use Anaconda Prompt to

• check the current working directory

• create a new working directory

• create subfolders inside it

• and start Jupyter notebook from the working directory

• Besides, you can also know how to create a Jupyter notebook in the working directory

An added explaination where is the data, 'gdp_china.csv' for next lecture.

This lecture talks how to read and save data. After this lecture, you will be able to

• read local and oneline data into Pandas Dataframe

• save Pandas DataFrame as a .CSV file into current working directory

You can find and download the 'gdp_china.csv' data from Downloadable Resources of this lecture.

This lecture talks about how to access basic information of dataframe in Pandas. After this lecture, you will be able to check the basic information on the dataframe, such as a summary of DataFrame information, date type, column names, the shape, a summary of some descriptive statistics, and so on.

This lecture shows how to change column names of the DataFrame. After this lecture, you will be able to change the column names with different methods.

This lecture shows how to slice data using different methods. After this lecture, you will be able to slice the data for your needs by rows or/and columns with different methods.

This lecture introduce some basic methods to sort the data. After this lecture, you will be able sort data in ascending or descending order to meet different requirements.

This lecture shows hoe to filter DataFrame and select different rows or/and columns using different methods. After this lecture, you will be able to filter the rows, or/ and columns you required with different methods, by column names, by regular expression, by conditions with methods of 'loc', 'where', 'query', 'eval', etc.

This lecture introduce some basic methods to group DataFrame. After this lecture, you will be able to group the dataframe to calculate summary statistics for each group.

This lecture talks about how to calculate summary statistics of DataFrame, or aggregation statistics. After this lecture, you will be clear what Summary statistics and Aggregation statistics are, and you will be able to calculate different aggregation statistics for different columns and groups with different methods.

This lecture will talk about how to detect the missing values of the dataset with different methods. After this lecture, you will able to find the missing data using different methods.

This lecture show you how to treate the missing values of data. After this lecture, you will be able to drop, or fill in the missings with different methods to meet different requirements.

This lecture shows how to dectect outliers in the data with some handy methods. After this lecture, you will able to use different methods to detect the outliers existing in a dataset.

This lecture talks about how to treat outliers in dataframe with some handy methods. After this lecture, you will be able to choose the methods to treate the outliers detected in the datasets.

This lectute shows you how to make correlation analysis and select variables for linear regression model through correlation analysis. After this leture, you will be able to analyze the correlations between variables through matrix scatterplot, correlation coefficients, correlation coefficient heatmap, and select the features for modelling.

This lecture displays how to encode categorical data. After this lecture, you will be able to encode the  categorical data using different methods based on your requirement.

This lecture talks about how to divide the dataset for modelling. After this lecture, you will be able to define independent variables and dependent variable, i.e features and target variable, and split the datasets for modelling estimation (training, or fitting) and modelling testing based on your need.

This lecture introduces the importance of normalization and different normalization methods. After this lecture, you will understand why data normalization is important and correct way to normalize the dataset, and you will be able to normalize your dataset with different scaling methods, and save and load the normalization scaler for new collected data for modelling prediction.

This lecture introduce the whole process of classic statistical modelling. After this lecture, you will be clear the  process for classic statistical modelling .

This lecture talks brief about data normalization in classic statistical regression. After this lecture, you will be clear how to choose the normalization scaler for classic statistical regression. The notes attached below are notes for all the rest of the lectures.

This lecture diplays how to define the model, fit the model and interprete the model results. After this lecture, you are able to develop your linear regression model using Statsmodels, and interprete the modelling results.

This lecture talks about the multicollinearity problem in multiple linear regression. After this lecture, you will be clear why multicollinearty harms the multiple linear regression model, and you will be able to detect this problem using some handy methods.

This lecture shows how to improve the model based on the problems. After this lecture, you will be able to assess your model results and improve your model.

This lecture demonstrates how to evaluate the developed model. After this lecture, you will be able to evaluate your model and test its predition ability, and diplay the comparision results between actural values and the prediction in dataframe.

This lecture illustrate how to visualize the modelling results with different plots. After this lecture, you will be able to choose different plotting methods to visualize your modelling results using Python Matplotlib, Seaborn, etc.

This lecture introduces you to the machine learning modelling process with Python. After this lecture, you will be clear about the proper process of machine learning modelling.

This lecture display how to define a machine learning linear regression model and train train it with Scikit Learn. After this lecture, you will be abel to define a linear regression, train it and assess the training results. The notes attached below contains the notes for all the rest lectures of this sections.

This lecture shows how to evaluate the model . After this lecture, you will be able to evaluate your model throught different statistics through your testing dataset and evaluate its prediction performance.

This lecture demonstrate the model improvement process. After this lecture, you will be able to judge if your model need to improve based on the evaluation results, and you can  improve your model using the methods introuduced in the lecture.

This lecture introduce several methods to visualize the modelling results. After this lecture, you will be able to visualize your modelling results with the methods introduced in this lecture.