Для работы Необходимо будет написать небольшую самостоятельную работу в GitHub, Python на англ на 20 минут. Что предполагается: Read the data set using pd.read_csv or ? method, depending on the type of data. Then display a few rows using “head”. By default we may have to change the number of r ws. . Build a frequency table for variable- calculate how many times we see each unique value and visualize it. The .plot method with specifying type (bar, horizontal bar chart etc.). Visualizing frequency table using bar chart. Using .groupby- may be asked to groupby by one or few columns (by one attribute, by one column of interest and by one/several aggregation function (.agg method where in brackets write with mean, mode etc.). Take 1 column of interest and calculate 1 or fee statistics (the agg function). Calculate mean, mode, median, st.d, variance etc. using the df []mode or describe method. Build a histogram using .hist or plot [kind set to us] Draw a boxplot, the IQR method. Or to implement the boxplot (calculate Q1, Q3, IQR, calculate min/max, outliers…). Be ready to implement it by hand using panda . To calculate quantile pandas: Quartile, quintile. df [ ] call.quantile. In the brackets right number (e.g 15% etc.) Find outliers using IQR method Interpret something: create condition, write down some conclusions (e.g. we can see a gap between the incomes etc.). Ссылки на материалы пройденные пришлю отдельно.