|
Python Data Science Training
Introduction
What is Python?
Installation and setup
Running Python programs
Python interpreter
Lists
Creating and manipulating lists
Indexing and slicing lists
List comprehensions
Dictionaries
Creating and manipulating dictionaries
Accessing and modifying dictionary items
Dictionary methods
Control statements
If statements
For loops
While loops
Break and continue statements
Functions
Creating and calling functions
Function parameters
Default arguments
Return statement
Variable scope
OOPS
Classes and objects
Attributes and methods
Inheritance
Polymorphism
Interface with various file types
XLSX
Reading and writing XLSX files
Formatting cells and worksheets
CSV
Reading and writing CSV files
Handling CSV data
Ability to extract text from PDF files
Libraries
Numpy
Creating and manipulating arrays
Indexing and slicing arrays
Numpy functions and methods
Pandas
Creating and manipulating dataframes
Indexing and slicing dataframes
Pandas functions and methods
Matplotlib
Basic plots
Customizing plots
Subplots
Basics of Statistics
Hypothesis testing
Null hypothesis
p-values
Type I and Type II errors
Fitting the curve
Linear regression
Nonlinear regression
Variance
Population variance
Sample variance
Standard deviation
Machine Learning
Linear regression
Simple linear regression
Multiple linear regression
Supervised learning
Decision trees
Random forests
Support vector machines
Naive Bayes
k-Nearest Neighbors
Unsupervised learning
Clustering
Principal Component Analysis
Singular Value Decomposition
ARIMA
Autoregressive Integrated Moving Average model
Projects
Predicting the stock market using Python
Stock Price Prediction: This project involves using historical data to develop a model for predicting stock prices. The model can be trained on various factors such as company financials, news sentiment, technical indicators, and economic indicators. The goal is to develop a model that can predict future stock prices with a high degree of accuracy.
.
Stock Price Crashing Detection
This project aims to build a predictive model that can detect when a stock is likely to experience a sudden and drastic drop in price. The model uses historical price and volume data, as well as news and sentiment analysis, to identify potential risk factors and predict the likelihood of a price crash.
.
Fraud Detection
This project involves developing a model to detect fraudulent transactions in real-time. The model can be trained on historical data to learn patterns of fraudulent behavior and can then be used to detect and flag suspicious transactions as they occur. This can help companies prevent fraud and minimize losses.
Web scraping with Python and Beautiful Soup
Introduction to web scraping
HTML and CSS basics
Extracting data from HTML with Beautiful Soup
Parsing and navigating HTML documents
Writing web scrapers with Python
Data cleaning and preprocessing techniques
Handling missing data
Outlier detection and removal
Data scaling and normalization
Handling categorical data
Dealing with imbalanced datasets
Model evaluation and selection
Cross-validation
Metrics for classification and regression
Overfitting and underfitting
Hyperparameter tuning
Ensemble methods
Time series analysis with Python
Introduction to time series data
Time series decomposition
Moving averages and smoothing techniques
ARIMA models
Exponential smoothing
SQL databases and Python
Connecting to databases with Python
Executing SQL queries with Python
Querying databases with Python libraries such as SQLAlchemy and PyMySQL
Data manipulation with SQL using Python
#378, 1st main, rajajinagar industrial planet honda showroom at bangalore - 560010
|
