adding tutorial, install documents

jegonzal · Dec 8, 2014 · 3d3cde9 · 3d3cde9
1 parent 26a8244
commit 3d3cde9
Show file tree

Hide file tree

Showing 134 changed files with 630 additions and 438 deletions.
diff --git a/BINARY_README b/BINARY_README
@@ -13,7 +13,7 @@ license/LICENSE.txt for details.
 Introduction
 ============
 
-GraphLab is a graph-based, high performance, distributed computation framework
+GraphLab PowerGraph is a graph-based, high performance, distributed computation framework
 written in C++.  
 
 GraphLab Features:
@@ -34,13 +34,6 @@ Learning Toolkits:     Tackle challenging machine
                        learning problems with ease
 
 
-For more details on the GraphLab see http://graphlab.org, including
-documentation, tutorial, etc.
-
-The source code and documentation for all applications can be found at 
-http://docs.graphlab.org/toolkits.html
-
-
 ========
 Mac OS X
 ========
@@ -49,7 +42,7 @@ distributed capabilities. All toolkits therefore run entirely on one machine
 in shared memory.
 
 These binaries have been tested to run on OS X 10.6 or greater. Though they
-may work on 10.5 as well. Please let us know if you encounter any issues.
+may work on 10.5 as well.
 
 =====
 Linux

diff --git a/README.md b/README.md
diff --git a/TUTORIALS.md b/TUTORIALS.md
diff --git a/apps/cascades/cascades.cpp b/apps/cascades/cascades.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/apps/concomp/concomp.cpp b/apps/concomp/concomp.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/apps/example/hello_world.cpp b/apps/example/hello_world.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/apps/label_propagation/label_propagation.cpp b/apps/label_propagation/label_propagation.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/images/800px-PageRank-hi-res-300x215.png b/images/800px-PageRank-hi-res-300x215.png
diff --git a/images/Slide1.jpg b/images/Slide1.jpg
diff --git a/images/als_eqn.gif b/images/als_eqn.gif
diff --git a/images/cloudcv-1024x489.png b/images/cloudcv-1024x489.png
diff --git a/images/collaborative_filtering.jpg b/images/collaborative_filtering.jpg
diff --git a/images/gl_os_software_stack.png b/images/gl_os_software_stack.png
diff --git a/images/kcore2-300x300.jpg b/images/kcore2-300x300.jpg
diff --git a/images/kmeans1.gif b/images/kmeans1.gif
diff --git a/images/panorama-1024x251.png b/images/panorama-1024x251.png
diff --git a/images/r-300x278.jpg b/images/r-300x278.jpg
diff --git a/images/topic-300x179.gif b/images/topic-300x179.gif
diff --git a/images/triangle_strong_community-150x150.jpg b/images/triangle_strong_community-150x150.jpg
diff --git a/images/triangle_weak_community-150x150.jpg b/images/triangle_weak_community-150x150.jpg
diff --git a/toolkits/README.md b/toolkits/README.md
@@ -0,0 +1,92 @@
+# Toolkits Overview
+
+## Collaborative Filtering
+
+![Collaborative Filtering](../images/collaborative_filtering.jpg?raw=true "collaborative_filtering")
+
+The collaborative filtering toolkit provides tools to identify patterns of user interests and make targeted recommendations. Learn more about collaborative filtering [here.](http://en.wikipedia.org/wiki/Collaborative_Filter)
+
+![ALS equation](../images/als_eqn.gif "als_eqn")
+
+Most of the algorithms take the rating matrix R, which is a sparse matrix holding the rating given by users to movies, and builds a linear model, finding two low dimensional matrices
+
+U and V s.t. their product approximates R: R ~ UV.
+
+We implement multiple collaborative filtering algorithms: ALS (Alternating least squares), SGD (Stochastic Gradient Descent) , Bias SGD, Weighted-ALS, Sparse-ALS, SVD++.
+
+## Clustering
+
+![](../images/kmeans1.gif "kmeans")
+
+## KMeans++
+
+GraphLab PowerGraph has a fast scalable implementation of the [Kmeans++](http://en.wikipedia.org/wiki/K-means%2B%2B) algorithm: a robust method of grouping datapoints into clusters.
+
+## Computer Vision
+
+![Image Stitching](../images/panorama-1024x251.png "Image Stitching")
+
+The Computer Vision Toolkit aims to provide fully distributed wrappers to algorithms in [OpenCV](http://opencv.org/ "OpenCV"), an open-source library aimed at real-time computer vision. Currently, the only implemented algorithm is Image-Stitching, where the goal is to create a composite panoramic image from a collection of images. Learn more about computer vision [here.](http://en.wikipedia.org/wiki/Computer_vision)
+
+GraphLab PowerGraph Computer Vision Toolkit has become it’s own spin-off project called [CloudCV](http://cloudcv.org "CloudCV"), a comprehensive system that will aims to provide access to state-of-the-art computer vision algorithms on the cloud.
+
+![CloudCV](../images/cloudcv-1024x489.png "CloudCV")
+
+CloudCV: Large-Scale Parallel Computer Vision on the Cloud
+
+
+## Graphical Models
+![](../doc/images/noisy_img.jpeg)
+![](../images/Slide1.jpg "Slide1")
+![](../doc/images/pred_img.jpeg)
+
+[Graphical models](http://en.wikipedia.org/wiki/Graphical_model) provide a compact interpretable representation of complex statistical phenomena by encoding random variables as vertices in a graph and relationships between those variables as edges. The Graphical Models toolkit provides a collection of methods to make predictions under uncertainty, and for reasoning about structured noisy data.
+
+The main components of Graphical Models toolkit are:
+
+1.  Distributed Dual Decomposition: performs maximum _a posteriori_ (MAP) inference in general [Markov Random Fields](http://en.wikipedia.org/wiki/Markov_random_field) via the Dual Decomposition algorithm. The MRF is assumed to be provided in the standard [UAI file format](http://www.cs.huji.ac.il/project/PASCAL/fileFormat.php). Maintained by [Dhruv Batra](http://filebox.ece.vt.edu/~dbatra/).
+2.  [Structured Prediction](http://docs.graphlab.org/graphical_models.html): that applies the [Loopy Belief propagation (LBP)](http://en.wikipedia.org/wiki/Belief_propagation) algorithm to a pair-wise [Markov Random Field](http://en.wikipedia.org/wiki/Markov_random_field) encoding the classic [Potts Model](http://en.wikipedia.org/wiki/Potts_model).
+
+## Graph Analytics
+
+![](../images/r-300x278.jpg "r")
+
+The Graph Analytics Toolkit aims to provide high performance, distributed tools for graph mining, for use in community detection, social network discovery, etc.
+
+The toolkit currently implements the following tools:
+
+### Triangle Counting
+![](../images/triangle_weak_community-150x150.jpg "triangle_weak_community")
+![](../images/triangle_strong_community-150x150.jpg "triangle_strong_community")
+
+
+Two triangle counting program:
+
+1.  **Undirected Triangle Counting**: counts the total number of triangles in a graph, or the the number of triangles each vertex is in
+2.  **Directed Triangle Counting:** Counts the number of types of triangles each vertex is in
+
+### PageRank
+
+![](../images/800px-PageRank-hi-res-300x215.png "800px-PageRank-hi-res")
+
+A classical graph algorithm which assigns each vertex a numerical importance value based on random walk properties. Learn more about page rank [here.](http://en.wikipedia.org/wiki/PageRank)
+
+### KCore Decomposition
+
+![](../images/kcore2-300x300.jpg "kcore")
+
+Identifies a hierarchical ordering of the vertices in the graph, allowing discovery of the central components of the network.
+
+## Topic Modeling
+
+![](../images/topic-300x179.gif "topic")
+
+## Latent Dirichlet Allocation
+
+The topic modelling toolbox currently implemented the [Latent Dirichlet Allocation](http://en.wikipedia.org/wiki/Latent_Dirichlet_allocation) algorithm for deriving semantic topic information from a corpus of plain text.
+
+## Linear Solvers
+
+GraphLab PowerGraph iterative solvers, for solving a linear system of the type Ax = b.
+
+Currently [Jacobi method](http://en.wikipedia.org/wiki/Jacobi_method) is implemented.
diff --git a/toolkits/clustering/clustering.dox b/toolkits/clustering/clustering.dox
@@ -1,4 +1,4 @@
-/**
+	/**
 
 \page clustering Clustering
 

diff --git a/toolkits/clustering/generate_synthetic.cpp b/toolkits/clustering/generate_synthetic.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/clustering/graph_laplacian_for_sc.cpp b/toolkits/clustering/graph_laplacian_for_sc.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/clustering/kmeans.cpp b/toolkits/clustering/kmeans.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/clustering/spectral_clustering.cpp b/toolkits/clustering/spectral_clustering.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/adpredictor.cpp b/toolkits/collaborative_filtering/adpredictor.cpp
@@ -14,14 +14,11 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  * Implementation of the adpredictor algorithm as given in the paper:
  * Web-Scale Bayesian Click-Through Rate Prediction for Sponsored Search Advertising in Microsoft’s Bing Search Engine
  * Thore Graepel, Joaquin Quinonero Candela, Thomas Borchert, and Ralf Herbrich
  * ICML 2010
- * Implemented by Danny Bickson, GraphLab Inc.
+ * Implemented by Danny Bickson, GraphLab, Inc.
  *
  */
 

diff --git a/toolkits/collaborative_filtering/als.cpp b/toolkits/collaborative_filtering/als.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/biassgd.cpp b/toolkits/collaborative_filtering/biassgd.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://graphlab.org
  *
  */
 

diff --git a/toolkits/collaborative_filtering/cdf.hpp b/toolkits/collaborative_filtering/cdf.hpp
@@ -14,8 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
-              http://graphlab.org
 */
 #ifndef CDF_HPP
 #define CDF_HPP

diff --git a/toolkits/collaborative_filtering/cosamp.hpp b/toolkits/collaborative_filtering/cosamp.hpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *  
  *  Code written by Danny Bickson, CMU
  *  Any changes to the code must include this original license notice in full.

diff --git a/toolkits/collaborative_filtering/doc.cpp b/toolkits/collaborative_filtering/doc.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/eigen_serialization.hpp b/toolkits/collaborative_filtering/eigen_serialization.hpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/eigen_wrapper.hpp b/toolkits/collaborative_filtering/eigen_wrapper.hpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://graphlab.org
  *
  */
 

diff --git a/toolkits/collaborative_filtering/make_synthetic_als_data.cpp b/toolkits/collaborative_filtering/make_synthetic_als_data.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/math.hpp b/toolkits/collaborative_filtering/math.hpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/nmf.cpp b/toolkits/collaborative_filtering/nmf.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/sgd.cpp b/toolkits/collaborative_filtering/sgd.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/sparse_als.cpp b/toolkits/collaborative_filtering/sparse_als.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/stats.hpp b/toolkits/collaborative_filtering/stats.hpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  * Class for collecting graph statistics
  */

diff --git a/toolkits/collaborative_filtering/svd.cpp b/toolkits/collaborative_filtering/svd.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/svdpp.cpp b/toolkits/collaborative_filtering/svdpp.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://graphlab.org
  *
  */
 

diff --git a/toolkits/collaborative_filtering/wals.cpp b/toolkits/collaborative_filtering/wals.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */
 

diff --git a/toolkits/collaborative_filtering/warp_als_coord.cpp b/toolkits/collaborative_filtering/warp_als_coord.cpp
@@ -14,9 +14,6 @@
  *  express or implied.  See the License for the specific language
  *  governing permissions and limitations under the License.
  *
- * For more about this software visit:
- *
- *      http://www.graphlab.ml.cmu.edu
  *
  */