- What is Analytics and Data Science
- Overview of Data Science and Analytics
- Why Analytics is becoming popular now.
- Application of Analytics in business
- Various Terminology in Analytics
- Various Analytics Methodology
- How businesses are using the power of Analytics.
- Various Analytics tools and their usage
Machine Learning classes in Wakad, Pune
Introduction to Data Science and Machine Learning
This is Beginners course which will introduce you to Data Science and Machine Learning areas, we will cover enough concepts for you to deep dive into various ML/AI areas such as EDA (Exploratory Data Analysis) NLP (Natural Language Processing), Deep Learning, computer vision, chatbots, etc.. Course Duration: approximately 2 Months (60 Hours) + practical (Self-Paced), we will guide you for practices and case studies.
-
Prerequisites for this course: Familiarity with the Python programming language Basic understanding of statistics, probability and linear algebra.
Course Duration: Instructor lead: 60 hours + Practical’s
Part 1
- Installing Python Anaconda Distribution
- Create Python environment
- Python native data types
- Basic programming concepts
- Python data science packages overview
- Data Types and Data objects/structures (strings, tuples, lists, dictionaries)
- Python Objects
- Math and Comparison Operators
- Conditional Statement
- Loops
- Functions
- Exception handling
- Understand Jupyter notebook and customize setting
- List and Dictionary Comprehensions
- Concept of Packages/Libraries – Important packages (NumPy, SciPy, Scikit-learn, Pandas, Matplotlib etc.)
- Installing and loading Packages and Name Spaces
- Reading and writing data
- Simple plotting
- What is Numpy?
- Importing Numpy
- Numpy overview
- Numpy Array creation and basic operation
- Numpy universal Functions
- Selecting and retrieving data
- Data slicing
- Iterating Numpy Data
- Shape Manipulations
- Stacking and Splitting Arrays
- Copies and Views: no copy, shallow copy, deep copy
- Indexing : Arrays of indices, Boolean Arrays
- Selecting data from Pandas DataFrame
- Slicing and dicing using Pandas
- GroupBy/Aggregate
- Strings with Pandas
- Dropdown and Select Operations
- Cleaning up messy data with Pandas
- Dropping Entries
- Selecting Entries
- Data Alignment
- Sorting and Ranking
- Summary Statistics
- Missing Values
- Merging data
- Concatenation
- Combining DataFrames
- Pivot
- Duplicates
- Binning
- Importing Pandas
- Pandas overview
- Object creation : Series Object , DataFrame Object
- View Data
- Selecting data by Label and Position
- Data Slicing
- Boolean Indexing
- Setting Data
Part-2
- Applying functions to data
- Histogramming
- String methods
- Merge Data: Concat, Join and Append
- Grouping and Aggregation
- Reshaping
- Analysing Data for missing values
- Filling missing values: fill with constant, forward filling, mean
- Removing Duplicates
- Transforming Data
- Anatomy of a MatplotLib Plot
- Matplotlib basic plots and it’s containers
- A Matplotlib figure, it’s components and properties
- Axes and other graphical objects
- Pylab and Pyplot,Data for Matplotlib Plots
- Axes and other graphical objects
- What is a Subplot?,Modifying size of figures
- Plotting routines with pyplot
- Customizing your pyplot,Deleting an Axes
- Setting up Plot Title, Axes Labels, Legend, Layout
- Customizing your pyplot,Deleting an Axes
- Showing, Saving and Closing your Plot
- Save a Plot to an image file and pdf file
- Use cla(), clf() or close
- Two areas of statistics in data science
- Applied statistics in business
- Descriptive Statistics
- Inferential Statistics,Data measurement scales
- Statistics terms and definitions
- Type of data,Quantitative vs Qualitative data
- Introduction to Regression
- Types of Regression
- Hands on of Regression with Python
- Correlation ,Weak and Strong Correlation
- Finding Correlation with Python
- Sampling Data, with and without replacement
- Sampling methods, Random vs Non-Random
- Using Page Object and Page Factory
- Measurement on Samples
- Random sampling methods
- Simple random, Stratified, Cluster, Systematic sampling
- Biased vs unbiased sampling
- Sampling Error
- Data Collection methods
- Measures of Central Tendencies
- Mean, Median and Mode
- Data Variability: Range, Quartiles, Standard Deviation
- Calculating Standard Deviation
- Z-Score/Standard Score
- Empirical Rule
- Calculating Percentiles
- Outliers
- Distribution Introduction
- Normal Distribution
- Central Limit Theorem
- Histogram – Normalization
- Other Distribution: Poisson, Binominal etc
- Normality testing
- Skewness
- Measure of Distance
- Euclidean, Manhattan and Minkowski Distance
- Hypothesis Testing
- Null Hypothesis, P-Value
- Need for Hypothesis Testing in Business
- Two tailed, Left tailed and Right tailed test
- Hypothesis Testing Outcomes: Type 1 & 2 errors
- Parametric vs Non-Parametric Testing
- Parametric Tests, T-Tests : One sample, two sample , paired
- One way ANOVA
- Importance of Parametric Tests
- Non Parametric Tests: Chi-Square, Mann-Whitney, Kruskal-Wallis etc
- Which Test to Choose?
- Ascerting accuracy of data
Part-3
- How to use Predictive Modeling in Python
- Linear Regression
- String methods
- Logistic Regression
- Model Selection
- Scoring
- Predictive Modeling Techniques
- Different phases of Predictive Modeling
- Business Case Study (Predictive Modeling )
- What is Machine Learning?
- Data Science Vs Machine Learning
- Fundamentals of Machine Learning
- Converting business problems to data problems
- Understand supervised and unsupervised learning with examples
- Understanding biases associated with any Machine Learning algorithm
- Drivers of Machine Learning algorithms
- Cost Functions
- Brief introduction to gradient descent
- Importance of model validation
- Overview of cross validation
- Model performance metrics
- K-Means Clustering: Theory, Euclidean method
- K-Means hands on with python
- K-Means Advantages and Disadvantages
- Simple Linear Regression: Implementing in Python, Working on use case
- Multiple Linear Regression: Implementing in python, Working on use case
- K-Nearest Neighbour: Implementing in Python, KNN advantages, working on use case
- Decision Trees: Implementing in python, Decision Tree Pros and Cons, Working on use case
- Tuning with hyper parameters
- Popular ML algorithms
- Clustering, Classification and regression
- Supervised vs unsupervised
- Choice of ML algorithm
- Grid Search vs Random search cross validation
- Key concepts of dimensionality reduction
- PCA theory
- Hands on coding
- Case study on PCA
- Key concepts of Random Forest
- Hands on coding
- Pros and Cons
- Case study on Random Forest
- Key concepts of Support Vector Machine
- Hands on coding
- Pros and Cons
- Correlation ,Weak and Strong Correlation
- Case study on SVM
- Key concepts of NLP
- Hands on coding
- Pros and Cons
- Text Processing with Vectorization
- Sentiment analysis with TextBlob
- Twitter sentiment analysis
- Key concept of Naïve Bayes
- Hands on coding
- Pros and Cons
- Naïve Bayes for text classification
- New articles tagging
- Basic ANN network for Regression and Classification
- Hands on coding
- Pros and Cons
- Case study on ANN, MLP
- TensorFlow demo
- Introduction to deep learning
