# Data Science Topics covered

**Plotting for Exploratory Data Analysis**[Duration : 10 Hours ]

- 2D,3D Scatter Plots
- Pair Plots
- Limitation of Pair Plots
- Histograms(Probability Density Functions)
- Univariate Analysis
- Cumulative Distribution Function
- Variance,SD,Range
- Percentiles and Quantiles
- Box-Plot with Whiskers
- Violin Plots
- Summary of Univariate,Bivariate and Multivariate Analysis
- Multivariate Probability Denisty Contour Plot
- Perform EDA

**Linear Algebra**[Duration : 10 Hours ]

- Introduction to Vectors,Row Vectors and Column Vectors
- Angle between two vectors
- Projection and Unit Vector
- Equation of Line , Plane and Hyperplane
- Distance of a point from Plane/Hyperplance and Half spaces
- Equation of a circle,Sphere and Hemisphere
- Equation of a Ellipse,Ellipsoid and Hyperellipsoid
- Square,Rectangle
- Hypercube ,Hyper Cuboid

**Probability and Statistics**[Duration : 10 Hours ]

- Introduction to Probability and Statistics
- Population and Sample
- Gaussian/ Normal Distribution and its PDF
- Cumulative Distribution Fuction of Guassian/Normal Distribution
- Symmetric Distribution,Skewness and Kurtosis
- Standard Normal Variate and Standardization
- Kernel Density Estimation
- Sampling Distribution and Central Limit theorm
- QQ plot – How to test if a random variable is normally distributed or not
- Discrete and Continuous Uniform Distributions
- How to randomly sample data points(Uniform Distribution)
- Bernouli and Binomial Distribution
- Log Normal Distribution
- Power Law Distribution
- Box Cox Transform
- Co-Variance
- Pearson Correlation Coefficient
- Chi-Square test
- Correlation Vs Causation
- Confidence Level Introduction
- Computing Confidence-Interval given distribution
- CI for mean of a normal random variable
- Confidence interval using bootstrapping
- Hypothesis testing methodology ,Null Hypothesis ,P-Value
- Re-Sampling and permutation test
- K-S test and K-S test for similarity for two distributions

**Dimensionality Reduction and Visualization**[Duration : 10 Hours ]

- What is Dimensionality reduction
- Row Vector and Column Vector
- How to represent a data set
- How to represent a data set as a matrix
- Data preprocessing – Column Normalization
- Mean of data matrix
- Data preprocessing :Column Standardization
- Co-Variance of a Data matrix

**Principal Component Analysis**[Duration : 10 Hours ]

- What is PCA
- Geometric Intuition of PCA
- Mathematical Objective Function of PCA
- Alternative Formulation of PCA :Distance minimization
- Eigen Values and Eigen Vectors
- PCA for Dimensionality Reduction and Visualization
- Limitation of PCA

**What is Machine Learning**[Duration : 10 Hours ]

- Machine Learning: What's the challenge?
- Acquainting yourself with the data
- What is, what isn't?
- Basic prediction model
- Classification, Regression, Clustering
- Classification, regression or clustering?
- Classification: Filtering spam
- Regression: LinkedIn views
- Clustering: Separating the iris species
- Supervised vs. Unsupervised
- Getting practical with supervised learning
- How to do unsupervised learning
- Tell the difference

**Performance menasures** [Duration : 10 Hours ]

- Measuring model performance or error
- The Confusion Matrix
- Deriving ratios from the Confusion Matrix
- The quality of a regression
- Adding complexity to increase quality
- Let's do some clustering!
- What to do with all these performance measures?
- Training set and test set
- Split the sets
- First you train, then you test
- Using Cross Validation
- How many folds?
- Bias and Variance
- Overfitting the spam!
- Increasing the bias
- Interpretability

**Classification**[Duration : 10 Hours ]

- Decision trees
- Learn a decision tree
- Understanding the tree plot
- Classify with the decision tree
- Pruning the tree
- Interpreting the tree
- Splitting criterion
- k-Nearest Neighbours
- Preprocess the data
- The knn() function
- K's choice
- Interpreting a Voronoi diagram
- The ROC curve
- Creating the ROC curve
- The area under the curve
- Interpreting the curves
- Comparing the methods

**Regression**[Duration : 10 Hours ]

- Regression: simple and linear!
- Simple linear regression: your first step!
- Performance measure: RMSE
- Performance measures: R-squared
- Another take at regression: be critical
- Non-linear, but still linear?
- Interpreting R-squared
- Multivariable Linear Regression
- Going all-in with predictors!
- Are all predictors relevant?
- Interpreting the residuals and p-values
- k-Nearest Neighbors and Generalisation
- Does your model generalize?
- Your own k-NN algorithm!
- Parametric vs non-parametric!

**Clustering**[Duration : 10 Hours ]

- Clustering with k-means
- k-means: how well did you do earlier?
- The influence of starting centroids
- Making a scree plot!
- What is your optimal k?
- Performance and scaling issues
- When to standardize your data?
- Standardized vs non-standardized clustering
- Hierarchical Clustering
- Did you get it all?
- Single Hierarchical Clustering
- Complete Hierarchical Clustering
- Hierarchical vs k-means
- Interpreting Dunn's Index
- Clustering US states based on criminal activity

**Association Rule Learning**[Duration : 2 Hours ]

- Apriori
- Eclat

**Reinforcement Learning**[Duration : 2 Hours ]

- Upper Confidence Bound (UCB)
- Thompson Sampling

**Natural Language Processing**[Duration : 2 Hours ]

**Deep Learning**[Duration : 12 Hours ]

- Artificial Neural Networks
- Convolutional Neural Networks

**Model Selection and Boosting**[Duration : 2 Hours ]

- Model Selection
- XGBoost

## Preferred Programming Languages Needed : R , Python

## Preferred Tools Needed : Tableau

Total Duration : 120 Hours

**Contact Details:**

# Mr. Vijay

# Mobile: 0091 94400 89341

# Phone: 0091 040-6456 8797

# Mexico/Canada/USA phone : 001 (650) 550-9178

# Register Online: moc.snoitulosdnimartceps|ofni#moc.snoitulosdnimartceps|ofni

# Email: ni.oc.oohay|pmpaqscyajiV#ni.oc.oohay|pmpaqscyajiV

**Yahoo chat :** Vijaycsqapmp

**Google chat/Skype chat/AOL chat/ICQ chat :** tiptopten2000

**Hotmail/Live chat / Rediff chat :** tiptopten

# http://spectramindsolutions.com

**Pls send us your query , will answer back within 24Hrs: Thanks in advance for contacting us**