Merge pull request #1 from hackseq/master

GitHub Pages

R/TextRankAnalysis.Rmd

@@ -1,8 +1,10 @@
 ---
 title: "TextRank"
 author: "Lucia Darrow"
-date: "October 19, 2019"
-output: html_document
+date: "19/10/2019"
+output: 
+  html_document:
+    toc: true
 ---
 
 ```{r setup, include=FALSE}
@@ -14,12 +16,15 @@ knitr::opts_chunk$set(echo = TRUE)
 library(data.table)
 library(textrank)
 library(udpipe)
+library(tidyverse)
+library(stringr)
+library(magrittr)
 ```
 
 
 ```{r import}
 
-termResults <- fread("./data/NGS.csv")
+termResults <- fread("../data/NGS.csv")
 termResults2019 <- termResults %>% filter(Year == 2019)
 
 ```

R/bigram_relationships.Rmd

@@ -1,8 +1,10 @@
 ---
 title: "Bigram Relationships"
 author: "Shannon Lo"
-date: "19 Oct 2019"
-output: html_document
+date: "19/10/2019"
+output: 
+  html_document:
+    toc: true
 ---
 
 ```{r Setup, include=FALSE}
@@ -22,6 +24,7 @@ library(tidygraph)
 ```
 
 The following function(s) are defined below:
+
   * **visualize_bigrams**: extracts bigrams from a text field, calculates frequency of bigrams, and creates a bigram plot to visualize relationships between words
     + *df_name*: name of dataframe that contains the text field of interest
     + *textfield*: name of text field (ie. column name)
@@ -78,6 +81,7 @@ visualize_bigrams <- function(df_name, textfield, topic_title){
 ```
 
 Read in the following data sources:
+
   * **Web scraped data**: this CSV contains information on journals and was created using *database_parallel2.R*
   * **Topics and search terms**: this CSV contains 10 topics and 3 search terms for each topic
 ```{r Read Data, results='hide'}
@@ -129,17 +133,64 @@ df_varcall <- df %>%
 ```
 
 Create bigram plots to visualize the relationships between two words. The darker lines represent higher frequency of occurrence.
-```{r Create Bigram Plots}
-#visualize_bigrams(df,abstract, "All Topics")
-visualize_bigrams(df_assembly, abstract, "Assembly")
-visualize_bigrams(df_databases, abstract, "Databases")
-visualize_bigrams(df_epigenetics, abstract, "Epigenetics")
-visualize_bigrams(df_geneexp, abstract, "Gene Expression")
-visualize_bigrams(df_genomeann, abstract, "Genome Annotation")
-visualize_bigrams(df_phylogenetics, abstract, "Phylogenetics")
-visualize_bigrams(df_seqal, abstract, "Sequence Alignment")
-visualize_bigrams(df_sequence, abstract, "Sequencing")
-visualize_bigrams(df_strucpred, abstract, "Structural Prediction")
-visualize_bigrams(df_varcall, abstract, "Variant Calling")
+
+## Assembly
+
+```{r Create Bigram Assembly}
+# visualize_bigrams(df,abstract, "All Topics")
+visualize_bigrams(df_assembly, abstract, "")
 ```
 
+## Databases
+
+```{r Create Bigram Database}
+visualize_bigrams(df_databases, abstract, "")
+```
+
+## Epigenetics
+
+```{r Create Bigram Epigenetics}
+visualize_bigrams(df_epigenetics, abstract, "")
+```
+
+## Gene Expression
+
+```{r Create Bigram Gene Expression}
+visualize_bigrams(df_geneexp, abstract, "")
+```
+
+## Genome Annotation
+
+```{r Create Bigram Genome Annotation}
+visualize_bigrams(df_genomeann, abstract, "")
+```
+
+## Phylogenetics
+
+```{r Create Bigram Phylogenetics}
+visualize_bigrams(df_phylogenetics, abstract, "")
+```
+
+## Sequence Alignment
+
+```{r Create Bigram Alignment}
+visualize_bigrams(df_seqal, abstract, "")
+```
+
+## Sequencing
+
+```{r Create Bigram Sequencing}
+visualize_bigrams(df_sequence, abstract, "")
+```
+
+## Structural Prediction
+
+```{r Create Bigram Structural Prediction}
+visualize_bigrams(df_strucpred, abstract, "")
+```
+
+## Variant Calling
+
+```{r Create Bigram Variant Calling}
+visualize_bigrams(df_varcall, abstract, "")
+```

R/general_vis.Rmd

@@ -1,8 +1,10 @@
 ---
 title: "General Visualizations"
-author: "Jasmine and Diana"
+author: "Jasmine Lai and Diana Lin"
 date: "20/10/2019"
-output: html_document
+output: 
+  html_document:
+    toc: true
 ---
 ```{r, include=FALSE}
 knitr::opts_chunk$set(echo = TRUE, error = FALSE, message = FALSE, warning = FALSE, fig.width=12, fig.height=8)
@@ -74,7 +76,7 @@ for (yr in 2003:2019) {
 ```
 
 The data is limited to the establishment of PLoS in 2003
-```{r racing bars animate, echo=TRUE}
+```{r racing bars animate, echo=FALSE}
 p <- ordered_df %>% 
   ggplot(aes(ordering, group = topic))+
   geom_tile(aes(y = cum_total/2,
@@ -89,7 +91,7 @@ p <- ordered_df %>%
   transition_states(Year, transition_length = 8, state_length = 4, wrap = FALSE) +
   ease_aes("cubic-in-out") +
 #aesthetics
-  labs(subtitle = "Trends in sequening methods",title = "Year {closest_state}", y = "cumulative total papers") +
+  labs(subtitle = "Trends in sequencing methods",title = "Year {closest_state}", y = "cumulative total papers") +
   theme(plot.background = element_blank(),
         legend.position = "none",
         axis.ticks.y = element_blank(),