---
output:
  pdf_document: default
  html_document: default
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_knit$set(root.dir = normalizePath("C:/Users/Dusty/Documents/coding/projects/Udacity/Data Analysis/eda/lesson5"))
library(ggplot2)
library(dplyr)
library(reshape2)
```

Lesson 5
========================================================

### Multivariate Data
Notes:

***

### Moira Perceived Audience Size Colored by Age
Notes:

***

### Third Qualitative Variable
Notes:

```{r Third Qualitative Variable}
pf = read.csv('pseudo_facebook.tsv', sep = '\t')
pf.fc_by_age_gender <- pf %>%
  filter(!is.na(gender)) %>%
  group_by(age, gender) %>%
  summarize(mean_friend_count = mean(friend_count),
            median_friend_count = median(friend_count),
            n = n()) %>%
  ungroup() %>%
  arrange(age)

head(pf.fc_by_age_gender)
```

***

### Plotting Conditional Summaries
Notes:

```{r Plotting Conditional Summaries}
ggplot(aes(x = age, y = median_friend_count), data = pf.fc_by_age_gender) +
  geom_line(aes(color = gender))
```

***

### Thinking in Ratios
Notes:

What is the ratio of friends for males vs females

### Wide and Long Format
Notes:

***

### Reshaping Data
Notes:

```{r}
#install.packages('reshape2')
pf.fc_by_age_gender.wide <- dcast(pf.fc_by_age_gender,
                                  age ~ gender,
                                  value.var = 'median_friend_count')

head(pf.fc_by_age_gender.wide)
```


***

### Ratio Plot
Notes:

```{r Ratio Plot}
ggplot(aes(x = age, y = female/male), data = pf.fc_by_age_gender.wide) +
  geom_line() +
  geom_hline(aes(yintercept = 1), alpha=0.3, linetype = 2)
```

***

### Third Quantitative Variable
Notes:

```{r Third Quantitative Variable}
pf$year_joined <- floor(2014 - pf$tenure/365)
head(pf)
```

***

### Cut a Variable
Notes:

```{r Cut a Variable}
pf$year_joined.bucket = cut(pf$year_joined, c(2004, 2009, 2011, 2012, 2014))
table(pf$year_joined.bucket)
```

***

### Plotting it All Together
Notes:

```{r Plotting it All Together}
ggplot(aes(x = age, y = friend_count), data = subset(pf, !is.na(year_joined.bucket))) +
  geom_line(aes(color = year_joined.bucket), stat='summary', fun.y = median)
```

***

### Plot the Grand Mean
Notes:

```{r Plot the Grand Mean}
ggplot(aes(x = age, y = friend_count), data = subset(pf, !is.na(year_joined.bucket))) +
  geom_line(aes(color = year_joined.bucket), stat='summary', fun.y = mean) +
  geom_line(stat = 'summary', fun.y = mean, linetype = 2)

```

***

### Friending Rate
Notes:

```{r Friending Rate}
with(subset(pf, tenure >= 1), summary(friend_count / tenure))
```

***

### Friendships Initiated
Notes:

What is the median friend rate?
0.2205

What is the maximum friend rate?
417.0

```{r Friendships Initiated}
ggplot(aes(y = friendships_initiated/tenure, x = tenure), data = subset(pf, tenure >= 1)) +
  geom_line(aes(color = year_joined.bucket), stat = 'summary', fun.y = mean)
```

***

### Bias-Variance Tradeoff Revisited
Notes:

```{r Bias-Variance Tradeoff Revisited}

#ggplot(aes(x = tenure, y = friendships_initiated / tenure),
#       data = subset(pf, tenure >= 1)) +
#  geom_line(aes(color = year_joined.bucket),
#            stat = 'summary',
#            fun.y = mean)
#
#ggplot(aes(x = 7 * round(tenure / 7), y = friendships_initiated / tenure),
#       data = subset(pf, tenure > 0)) +
#  geom_line(aes(color = year_joined.bucket),
#            stat = "summary",
#            fun.y = mean)
#
#ggplot(aes(x = 30 * round(tenure / 30), y = friendships_initiated / tenure),
#       data = subset(pf, tenure > 0)) +
#  geom_line(aes(color = year_joined.bucket),
#            stat = "summary",
#            fun.y = mean)
#
#ggplot(aes(x = 90 * round(tenure / 90), y = friendships_initiated / tenure),
#       data = subset(pf, tenure > 0)) +
#  geom_line(aes(color = year_joined.bucket),
#            stat = "summary",
#            fun.y = mean)

ggplot(aes(x = tenure, y = friendships_initiated / tenure),
       data = subset(pf, tenure >= 1)) +
  geom_smooth(aes(color = year_joined.bucket))

```

***

### Sean's NFL Fan Sentiment Study
Notes:

***

### Introducing the Yogurt Data Set
Notes:

***

### Histograms Revisited
Notes:

```{r Histograms Revisited}
yo <- read.csv('yogurt.csv')

yo$id <- factor(yo$id)
head(yo)

ggplot(aes(x = price), data = yo) +
  geom_histogram()
```

***

### Number of Purchases
Notes:

```{r Number of Purchases}
yo <- transform(yo, all.purchases = strawberry + blueberry + pina.colada + plain + mixed.berry)
head(yo)
```

***

### Prices over Time
Notes:

```{r Prices over Time}
ggplot(aes(x = time, y = price), data = yo) +
  geom_point(alpha = 1/10)

ggplot(aes(x = time, y = price), data = yo) +
  geom_point(alpha = 1/10, aes(color = all.purchases))
```

***

### Sampling Observations
Notes:

***

### Looking at Samples of Households

```{r Looking at Sample of Households}
set.seed(1)
sample.ids <- sample(levels(yo$id), 16)

ggplot(aes(x = time, y = price), data = subset(yo, id %in% sample.ids)) +
  facet_wrap( ~ id) +
  geom_line() +
  geom_point(aes(size = all.purchases), pch = 1)
```

***

### The Limits of Cross Sectional Data
Notes:

***

### Many Variables
Notes:

***

### Scatterplot Matrix
Notes:

```{r}
#install.packages('GGally')
library(GGally)
theme_set(theme_minimal(20))

set.seed(1836)
pf_subset <- pf[, c(2:15)]
names(pf_subset)
ggpairs(pf_subset[sample.int(nrow(pf_subset), 1000), ])
```

### Even More Variables
Notes:

***

### Heat Maps
Notes:

```{r}
nci <- read.table("nci.tsv")
colnames(nci) <- c(1:64)
```

```{r}
nci.long.samp <- melt(as.matrix(nci[1:2000,]))
names(nci.long.samp) <- c("gene", "case", "value")
head(nci.long.samp)

ggplot(aes(y = gene, x = case, fill = value),
  data = nci.long.samp) +
  geom_tile() +
  scale_fill_gradientn(colours = colorRampPalette(c("blue", "red"))(100))
```


***

### Analyzing Three of More Variables
Reflection:

***

Click **KnitHTML** to see all of your hard work and to have an html
page of this lesson, your answers, and your notes!