import matplotlib.

pyplot as plt

fig, ax = plt.subplots()
plt.show()

seattle_weather["MONTH"]
1 Jan
2 Feb
3 Mar
...
12 Dec
seattle_weather["MLY-TAVG-NORMAL"]
1 42.1
2 43.4
3 46.6
...
12 41.1

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])
plt.show()

ax.plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
plt.show()

fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])
ax.plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
plt.show()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"])
plt.show()

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], marker="o")

plt.show()

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], marker="v")

plt.show()

fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"], marker="v", linestyle="--")
plt.show()

fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"], marker="v", linestyle="None")
plt.show()
fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"], marker="v", linestyle="--", color=
plt.show()

ax.set_xlabel("Time (months)")
ax.set_ylabel("Average temperature (Fahrenheit degrees)")
plt.show()

ax.set_title("Weather in Seattle")
plt.show()

fig, ax = plt.subplots(3, 2)
plt.show()

ax[0, 0].plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], color='b')

plt.show()
fig, ax = plt.subplots(2, 1, sharey=True)
plt.show()

plt

plt

plt.subplots()
 Axes.plot()

plt.show()
 Axes.plot()

Axes.plot()

plt.show()

Axes.plot()

Axes.plot()

plt.show()

marker

"o"

"v"

linestyle

"--"
 "None" linestyle

"r"

set_

set_xlabel

set_ylabel

set_title
 subplots

Figure

Axes

ax
 plot

sharey

sharey
date,co2,relative_temp
1958-03-06,315.71,0.1
1958-04-06,317.45,0.01
...
2016-12-06,404.45,0.81

DatetimeIndex

climate_change.index
DatetimeIndex(['1958-03-06', '1958-04-06', ..., '2016-12-06'], dtype='datetime64[ns]', name='date', length

import matplotlib.pyplot as plt

fig, ax = plt.subplots()
 ax.plot(climate_change.index, climate_change['co2'])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')
plt.show()

sixties = climate_change["1960-01-01":"1969-12-31"]
fig, ax = plt.subplots()
ax.plot(sixties.index, sixties['co2'])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')
plt.show()

sixty_nine = climate_change["1969-01-01":"1969-12-31"]
fig, ax = plt.subplots()
ax.plot(sixty_nine.index, sixty_nine['co2'])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')
plt.show()

fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change["co2"])
ax.plot(climate_change.index, climate_change["relative_temp"])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm) / Relative temperature')
plt.show()
fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change["co2"])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')

ax2 = ax.twinx()
ax2.plot(climate_change.index, climate_change["relative_temp"])
ax2.set_ylabel('Relative temperature (Celsius)')
plt.show()

fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change["co2"], color='blue')
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)', color='blue')
ax.tick_params('y', colors='blue')

ax2 = ax.twinx()
ax2.plot(climate_change.index, climate_change["relative_temp"], color='red')
ax2.set_ylabel('Relative temperature (Celsius)', color='red')
ax2.tick_params('y', colors='red')
plt.show()

def plot_timeseries(axes, x, y, color, xlabel, ylabel):

axes.plot(x, y, color=color)
axes.set_xlabel(xlabel)
axes.set_ylabel(ylabel, color=color)
axes.tick_params('y', colors=color)
fig, ax = plt.subplots()
plot_timeseries(ax, climate_change.index, climate_change['co2'], 'blue', 'Time', 'CO2 (ppm)')
ax2 = ax.twinx()
plot_timeseries(ax2, climate_change.index, climate_change['relative_temp'], 'red', 'Time', 'Relative temperatur
plt.show()

ax2.annotate(">1 degree", xy=(pd.Timestamp("2015-10-06"), 1))

ax2.annotate(">1 degree",
xy=(pd.Timestamp('2015-10-06'), 1),
xytext=(pd.Timestamp('2008-10-06'), -0.2),
arrowprops={"arrowstyle":"->", "color":"gray"})
index_col
twinx

plot

set_ylabel

tick_params

plot_timeseries def
plot set_xlabel set_ylabel tick_params
annotate

xytext

arrowprops
medals = pd.read_csv('medals_by_country_2016.csv', index_col=0)
fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
plt.show()

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
plt.show()

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
ax.bar(medals.index, medals["Silver"], bottom=medals["Gold"])
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
plt.show()

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
ax.bar(medals.index, medals["Silver"], bottom=medals["Gold"])
ax.bar(medals.index, medals["Bronze"], bottom=medals["Gold"] + medals["Silver"])
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
plt.show()
fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"], label="Gold")
ax.bar(medals.index, medals["Silver"], bottom=medals["Gold"], label="Silver")
ax.bar(medals.index, medals["Bronze"], bottom=medals["Gold"] + medals["Silver"], label="Bronze")
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
ax.legend()
plt.show()

fig, ax = plt.subplots()
ax.bar("Rowing", mens_rowing["Height"].mean())
ax.bar("Gymnastics", mens_gymnastics["Height"].mean())
ax.set_ylabel("Height (cm)")
plt.show()

fig, ax = plt.subplots()
ax.hist(mens_rowing["Height"])
ax.hist(mens_gymnastics["Height"])
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
plt.show()

ax.hist(mens_rowing["Height"], label="Rowing")
ax.hist(mens_gymnastics["Height"], label="Gymnastics")
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
ax.legend()
plt.show()
ax.hist(mens_rowing["Height"], label="Rowing", bins=5)
ax.hist(mens_gymnastics["Height"], label="Gymnastics", bins=5)
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
ax.legend()
plt.show()

ax.hist(mens_rowing["Height"], label="Rowing",
bins=[150, 160, 170, 180, 190, 200, 210])
ax.hist(mens_gymnastics["Height"], label="Gymnastics",
bins=[150, 160, 170, 180, 190, 200, 210])
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
ax.legend()
plt.show()

ax.hist(mens_rowing["Height"], label="Rowing",
bins=[150, 160, 170, 180, 190, 200, 210],
histtype="step")
ax.hist(mens_gymnastics["Height"], label="Gymnastics",
bins=[150, 160, 170, 180, 190, 200, 210],
histtype="step")
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
ax.legend()
plt.show()
fig, ax = plt.subplots()
ax.bar("Rowing", mens_rowing["Height"].mean(), yerr=mens_rowing["Height"].std())
ax.bar("Gymnastics", mens_gymnastics["Height"].mean(), yerr=mens_gymnastics["Height"].std())
ax.set_ylabel("Height (cm)")
plt.show()

fig, ax = plt.subplots()
ax.errorbar(seattle_weather["MONTH"],
seattle_weather["MLY-TAVG-NORMAL"],
yerr=seattle_weather["MLY-TAVG-STDDEV"])
ax.errorbar(austin_weather["MONTH"],
austin_weather["MLY-TAVG-NORMAL"],
yerr=austin_weather["MLY-TAVG-STDDEV"])
ax.set_ylabel("Temperature (Fahrenheit)")
plt.show()

fig, ax = plt.subplots()
ax.boxplot([mens_rowing["Height"], mens_gymnastics["Height"]])
ax.set_xticklabels(["Rowing", "Gymnastics"])
ax.set_ylabel("Height (cm)")
plt.show()

fig, ax = plt.subplots()
ax.scatter(climate_change["co2"], climate_change["relative_temp"])
ax.set_xlabel("CO2 (ppm)")
ax.set_ylabel("Relative temperature (Celsius)")
plt.show()
eighties = climate_change["1980-01-01":"1989-12-31"]
nineties = climate_change["1990-01-01":"1999-12-31"]
fig, ax = plt.subplots()
ax.scatter(eighties["co2"], eighties["relative_temp"],
color="red", label="eighties")
ax.scatter(nineties["co2"], nineties["relative_temp"],
color="blue", label="nineties")
ax.legend()
ax.set_xlabel("CO2 (ppm)")
ax.set_ylabel("Relative temperature (Celsius)")
plt.show()

fig, ax = plt.subplots()
ax.scatter(climate_change["co2"], climate_change["relative_temp"],
c=climate_change.index)
ax.set_xlabel("CO2 (ppm)")
ax.set_ylabel("Relative temperature (Celsius)")
plt.show()

## Quantitative Comparisons: Bar Charts

### Overview of Quantitative Comparisons

> "In this chapter, we will focus on quantitative comparisons between parts of the data."

### Olympic Medals Dataset

- The dataset contains information about the number of medals won by several countries in the **2016 Olympic Ga
- Though the dataset is small, making comparisons between countries can be challenging without visualization

### Visualizing Olympic Medals Data

1. **Reading the Data**:

- Use **Pandas** to create a DataFrame from a file containing the medal data.
- The first column, containing country names, is set as the index for the DataFrame.

2. **Creating a Bar Chart for Gold Medals**:

- A **Figure** and **Axes** object are created.
- The `Axes.bar()` method is called to generate a bar chart representing the number of gold medals.
- The height of each bar corresponds to the values in the "Gold" column of the DataFrame.
- The x-axis ticks are labeled with country names from the DataFrame index.
### Adjusting the Chart for Readability

- **Rotating Tick Labels**:

- Use the `set_xticklabels()` method to rotate the labels by **90 degrees** for better readability.
- Add a label to the y-axis indicating that the height corresponds to the number of medals.

### Visualizing Other Medals

1. **Adding Silver and Bronze Medals**:

- To display silver and bronze medals in the same plot, create a **stacked bar chart**.
- The process starts similarly to the gold medals:
- Call `bar()` for the "Silver" column and use the `bottom` keyword argument to stack it on top of the gol

2. **Including Bronze Medals**:

- Add another call to `bar()` for the bronze medals, setting the `bottom` to the sum of gold and silver meda

### Full Stacked Bar Chart

- The final chart displays all three medal categories (Gold, Silver, Bronze) stacked for each country.

### Adding a Legend for Clarity

- To improve the chart's readability:

1. Add the `label` keyword argument to each `bar()` call to specify what each color represents.
2. Use the `Axes.legend()` method before calling `plt.show()` to display a legend indicating which color corr

### Final Stacked Bar Chart with Legend

- The completed figure includes a legend that clarifies the meaning of each bar color.

### Interactive Component

> "Now, you try!"

This encourages students to apply what they've learned by creating their own bar chart based on the concepts di

## Quantitative Comparisons: Scatter Plots

### Bar Charts vs. Bi-variate Comparisons

> "Bar charts show us the values of one variable across different conditions, such as different countries. But

### Introducing Scatter Plots

- **Definition**: A scatter plot is a standard visualization used for bi-variate comparisons.

- **Example**: Using climate change data:
- One column contains measurements of carbon dioxide.
 - Another column contains concurrent measurements of relative temperature.
- **Plot Representation**: Each measurement is represented as a point:
- **X-axis**: Distance representing the carbon dioxide measurement.
- **Y-axis**: Height representing the temperature measurement.

#### Steps to Create a Scatter Plot:

1. Initialize a Figure and Axes objects.

2. Call the Axes scatter method:
- First argument: X-axis data (carbon dioxide).
- Second argument: Y-axis data (temperature).
3. Set axis labels for interpretation.
4. Display the figure using `plt.show()`.

### Customizing Scatter Plots

> "We can customize scatter plots in a manner that is similar to the customization that we introduced in other

- **Objective**: Show two bivariate comparisons side-by-side.

- **Data Selection**: Use time-series indexing to create two DataFrames:
- **DataFrame for the 1980s**:
- Color: Red
- Label: "eighties"
- **DataFrame for the 1990s**:
- Color: Blue
- Label: "nineties"
- **Adding Data to Axes**:
- First, add the 1980s data.
- Then, add the 1990s data.
- **Legend**: Use the legend method to distinguish between the two datasets.
- **Display**: Set axis labels and call `plt.show()`.

### Encoding a Comparison by Color

> "You can see that the relationship between temperatures and carbon dioxide didn't change much during these ye

- **Visual Distinction**: Color can be used effectively for comparison.

### Encoding a Third Variable by Color

- **Extended Comparison**: Color can also represent a third variable.

- **Example**: In the climate change data, time is represented as a continuous variable in the DataFrame index
- **Implementation**:
- Use the `c` keyword argument to encode time as color.
- Note: This is different from the previously used color keyword argument.

### Encoding Time in Color

- **Color Brightness**: The brightness of the color applied to the points indicates the time of measurements
- Dark blue points represent earlier measurements.
- Bright yellow points represent later measurements.

### Practice Making Your Own Scatter Plots!

> "In the exercises, go ahead and practice making your own scatter plots."

## Quantitative Comparisons: Histograms

### Bar Charts vs. Histograms

> "Bar-charts show us the value of a variable in different conditions. Now, we're going to look at histograms.

### Histograms

- Histograms display the distribution of a variable's values.

- Example: Data from the **2016 Olympic Games**:
- Two DataFrames extracted:
- Medal winners in **men's gymnastics**
- Medal winners in **men's rowing**
- Data includes:
- Types of medals won
- Competitor's height and weight

### Bar Chart Comparison

- A bar chart can be used to compare heights.

- Steps to create a bar chart:
1. Create **Figure** and **Axes** objects.
2. Add bars representing the mean heights:
- Rowing "Height" column
- Gymnastics "Height" column
3. Set the **y-axis label** and display the figure.

### Introducing Histograms

- Histograms provide a full distribution of values for each variable.

- Steps to create a histogram:
1. Initialize **Figure** and **Axes**.
2. Call the **Axes hist** method with the "Height" column of:
- Men's rowing DataFrame
- Men's gymnastics DataFrame
- **X-axis**: Values within the variable.
- **Height of bars**: Number of observations in each bin of values.
- Example observations:
- 12 gymnasts between 164 and 167 cm (highest bar = 12 units).
- 20 rowers between 188 and 192 cm (highest bar = 20 units).
### Importance of Labels

> "Because the x-axis label no longer provides information about which color represents which variable, labels

- To label a variable:
- Use the **label** keyword argument in the hist method.
- Call the **legend** method before **plt.show()** to display the legend.

### Customizing Histograms: Setting the Number of Bins

- Default number of bins in a histogram: **10**.

- To customize:
- Provide an integer to the **bins** keyword argument.

### Customizing Histograms: Setting Bin Boundaries

- Provide a sequence of values to set specific boundaries between bins.

### Customizing Histograms: Transparency

- To reduce occlusion of data:

- Change the histogram type from **bar** to **step** using:
- `histtype='step'`
- This displays the histogram as thin lines instead of solid bars.

### Example: Histogram with a Histtype of Step

- Allows clearer visibility of data, confirming there are rowers with a height of less than 180 cm.

### Create Your Own Histogram!

- Upcoming exercises will allow you to create your own histograms.

## Statistical Plotting

### Statistical Plotting Overview

Statistical plotting is a set of methods for using visualization to make comparisons. It allows us to formalize

### Adding Error Bars to Bar Charts

**Error Bars**
Error bars are additional markers on a plot or bar chart that provide information about the distribution of the

- **Purpose:** Summarize the distribution in one number, such as the standard deviation.
- **Example Data:** Heights of medalists in the 2016 Olympic Games.
**Implementation in Bar Chart**
To add error bars to a bar chart, use the `ax.bar` method:
- **Arguments:**
- `x`: Position of the bars
- `y`: Mean of the data (e.g., mean of the "Height" column)
- `yerr`: Standard deviation of the data (e.g., standard deviation of the "Height" column)

### Visualization of Error Bars in Bar Chart

The bar chart with error bars summarizes:

- **Mean Value:** Central tendency of the data
- **Spread of Values:** Quantified as standard deviation

### Adding Error Bars to Plots

Error bars can also be added to line plots using the `Axes.errorbar` method.

**Implementation in Line Plot**

To plot data with error bars:
- **Arguments:**
- `x`: Sequence of x values (e.g., "MONTH" column)
- `y`: Sequence of y values (e.g., column with average monthly temperatures)
- `yerr`: Column containing standard deviations of the average monthly temperatures

### Visualization of Error Bars in Line Plot

This method adds vertical markers to the plot, indicating variability in the data.

### Adding Boxplots

**Boxplot**
A boxplot is a statistical visualization technique invented by John Tukey, known as a pioneer in data science

**Implementation**
To create a boxplot:
- Use the boxplot method of the Axes object.
- Pass a list of sequences (e.g., "Height" columns from men's rowing and gymnastics).
- Label the y-axis separately.

### Interpreting Boxplots

A boxplot displays several key features of the distribution:

- **Median Height:** Indicated by a red line within the box.

- **Inter-Quartile Range (IQR):** The box edges represent the 25th and 75th percentiles.
- **Whiskers:** Extend to one and a half times the size of the IQR beyond the 25th and 75th percentiles,
- **Outliers:** Points beyond the whiskers indicate values that are unusually high or low compared to the major
**Example:** In the sample, there are three unusually short rowers and one unusually tall gymnast.

### Exercises

Students are encouraged to create their own statistical visualizations to apply the techniques discussed

### Preparing Your Figures to Share

#### Changing Plot Style

To change the plot style in Matplotlib, use the following code:
```python
import matplotlib.pyplot as plt
fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])
ax.plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
ax.set_xlabel("Time (months)")
ax.set_ylabel("Average temperature (Fahrenheit degrees)")
plt.show()

plt.style.use("ggplot")

plt.style.use("bmh")
plt.style.use("seaborn-colorblind")

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
plt.show()

fig.savefig("gold_medals.png")

ls
fig.savefig("gold_medals.jpg")
fig.savefig("gold_medals.jpg", quality=50)
fig.savefig("gold_medals.svg")

fig.savefig("gold_medals.png", dpi=300)

fig.set_size_inches([5, 3])

fig.set_size_inches([3, 5])
sports = summer_2016_medals["Sport"].unique()
print(sports)

fig, ax = plt.subplots()

for sport in sports:

sport_df = summer_2016_medals[summer_2016_medals["Sport"] == sport]
ax.bar(sport, sport_df["Height"].mean(),
yerr=sport_df["Height"].std())

ax.set_ylabel("Height (cm)")
ax.set_xticklabels(sports, rotation=90)
plt.show()

seaborn.relplot(x="horsepower", y="mpg", hue="origin", size="weight",

sizes=(40, 400), alpha=.5, palette="muted",
 height=6, data=mpg)

## Preparing Your Figures to Share with Others

### Customization of Figure Styles

> "This chapter will focus on creating visualizations that you can share with others and incorporate into autom

- The appearance of individual elements of a figure can be customized, including:

- Line color
- Marker shapes

### Changing Plot Style

> "To see what that means, let's look at one of the figures we created in a previous lesson."

- The overall style of the figure can be changed to significantly alter its appearance.
- Example: A figure showing average temperatures in Seattle and Austin as a function of the months of the year

### Choosing a Style

> "If instead, we add this line of code before the plotting code, the figure style will look completely differe

- Adding a specific line of code allows for the emulation of styles from other libraries, such as **ggplot
- The chosen style affects multiple elements:
- Different colors
- Different fonts
- An added gray background with a faint white grid marking the x-axis and y-axis tick locations
- The selected style applies to all figures in the current session until changed.

### Back to the Default

> "For example, to go back to the default style, you would run plt.style.use('default')."

- Use the command `plt.style.use('default')` to revert to the default plotting style.

### The Available Styles

> "Matplotlib contains implementations of several different styles."

- A range of styles can be explored through a dedicated webpage showcasing visualizations created with each sty

| Style Name | Description |

|----------------------|--------------------------------------------------------------|
| **bmh** | Example of the "bmh" style's appearance |
| **seaborn-colorblind**| Style that enhances visibility for colorblind individuals |

### Seaborn Styles

> "In fact, if you visit the documentation web-page, you will see that there are several available styles that

- Seaborn is a statistical visualization library based on Matplotlib.

- Matplotlib adopts several styles developed in Seaborn, enhancing visualizations.

### Guidelines for Choosing Plotting Style

> "How would you choose which style to use?"

- **Visibility Considerations**:
- Dark backgrounds are typically discouraged unless necessary.

- **Color Considerations**:
- Use colorblind-friendly styles (e.g., **seaborn-colorblind**, **tableau-colorblind10**) to accommodate appr

- **Medium Considerations**:
- Design figures with the intended medium in mind:
- For printed reports, avoid colored backgrounds that consume more ink.
- Consider using the **grayscale** style for black-and-white printers to maintain visual differences

### Practice Choosing the Right Style

> "In the exercises, you'll practice selecting some of these styles for your own visualizations."

## Sharing Your Visualizations

> "After you have created your visualizations, you are ready to share them with your collaborators, colleagues,

### Final Customizations

- Important to finalize customizations to your figures before sharing.

## A Figure to Share

- Example figure displays data about the **number of gold medals** won by various countries in the **2016
- The code previously used `plt.show()` to display the figure on screen.

## Saving the Figure to File

- Replace `plt.show()` with the `Figure` object's `savefig` method.

- Input a file name for the function, e.g., `"gold_medals.png"`.
- The figure will save as a file on your filesystem instead of displaying on the screen.

### Example Command

- Use UNIX command `ls` to verify the saved file in the current working directory.
## Different File Formats

| Format | Compression Type | Use Case | Notes

|--------------|------------------|---------------------------------------------------|-----------------
| **PNG** | Lossless | General-purpose and high-quality images | Retains high quality bu
| **JPG** | Lossy | Images for websites | Adjustable quality
| **SVG** | Vector graphics | Editable images for advanced graphics software | Good for post-

## Resolution

- Control image quality using the `dpi` keyword argument (dots per inch).
- Higher `dpi` results in higher quality; for example, setting `dpi = 300` yields high quality.

### File Size Consideration

- Increased resolution leads to larger file sizes.

## Figure Size and Aspect Ratio

- Adjust figure size using `set_size_inches` method.

- Takes a sequence of numbers: first for width, second for height.

### Example Aspect Ratios

- Wide and short

- Long and narrow

## Practice Saving Your Visualizations!

- Exercises will follow to practice saving visualizations as files.

## Automating Figures from Data

### Strengths of Matplotlib

> "One of the strengths of Matplotlib is that, when programmed correctly, it can flexibly adapt to the inputs t

### Why Automate?

- **Flexibility**: Write functions and programs that automatically adjust based on input data.
- **Efficiency**: Automation allows for quicker figure creation compared to traditional graphical user interfac
- **Robustness**: Programs can inspect incoming data and change behaviors accordingly.
- **Reproducibility**: Automatic adjustments provide consistent behavior across different runs.

### Understanding Data Variability

#### Different Kinds of Data

- Consider a dataset about **Olympic medal winners**.
- There may be various branches of sports included in new data files, which may not be known in advance.

### Getting Unique Values of a Column

- In a pandas DataFrame, a column is a pandas Series object.

- To identify distinct sports in the data, use the `unique` method:

```python
unique_sports = df['Sport'].unique()

sport

sport_df

bar
import matplotlib.pyplot as plt

fig, ax = plt.subplots()
plt.show()
 seattle_weather["MONTH"]
1 Jan
2 Feb
3 Mar
4 Apr
5 May
6 Jun
7 Jul
8 Aug
9 Sep
10 Oct
11 Nov
12 Dec

seattle_weather["MLY-TAVG-NORMAL"]
1 42.1
2 43.4
3 46.6
4 50.5
5 56.0
6 61.0
7 65.9
8 66.5
9 61.6
10 53.3
11 46.2
12 41.1

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])
plt.show()

ax.plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
plt.show()

fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])
ax.plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
plt.show()

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"])
plt.show()

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], marker="o")

plt.show()

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], marker="v")

plt.show()

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"], marker="v", linestyle="--")

plt.show()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"], marker="v", linestyle="None")
plt.show()

ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"], marker="v", linestyle="--", color

plt.show()

ax.set_xlabel("Time (months)")
plt.show()

ax.set_ylabel("Average temperature (Fahrenheit degrees)")

plt.show()

ax.set_title("Weather in Seattle")
plt.show()

fig, ax = plt.subplots(3, 2)
plt.show()
ax[0, 0].plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], color='b')
plt.show()

fig, ax = plt.subplots(2, 1)
ax[0].plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], color='b')
ax[0].plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-25PCTL"], linestyle='--', color='b')
ax[0].plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-75PCTL"], linestyle='--', color='b')
ax[1].plot(austin_weather["MONTH"], austin_weather["MLY-PRCP-NORMAL"], color='r')
ax[1].plot(austin_weather["MONTH"], austin_weather["MLY-PRCP-25PCTL"], linestyle='--', color='r')
ax[1].plot(austin_weather["MONTH"], austin_weather["MLY-PRCP-75PCTL"], linestyle='--', color='r')
ax[0].set_ylabel("Precipitation (inches)")
ax[1].set_ylabel("Precipitation (inches)")
ax[1].set_xlabel("Time (months)")
plt.show()

fig, ax = plt.subplots(2, 1, sharey=True)

 DatetimeIndex

climate_change.index
DatetimeIndex(['1958-03-06', '1958-04-06', '1958-05-06', ...],
dtype='datetime64[ns]', name='date', length=706, freq=None)

climate_change['relative_temp']
climate_change['co2']

import matplotlib.pyplot as plt

fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change['co2'])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')
plt.show()
sixties = climate_change["1960-01-01":"1969-12-31"]
fig, ax = plt.subplots()
ax.plot(sixties.index, sixties['co2'])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')
plt.show()

sixty_nine = climate_change["1969-01-01":"1969-12-31"]
fig, ax = plt.subplots()
ax.plot(sixty_nine.index, sixty_nine['co2'])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')
plt.show()

import pandas as pd
climate_change = pd.read_csv('climate_change.csv',
parse_dates=["date"],
index_col="date")

fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change["co2"])
ax.plot(climate_change.index, climate_change["relative_temp"])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm) / Relative temperature')
plt.show()
fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change["co2"])
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)')

ax2 = ax.twinx()
ax2.plot(climate_change.index, climate_change["relative_temp"])
ax2.set_ylabel('Relative temperature (Celsius)')
plt.show()

fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change["co2"], color='blue')
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)', color='blue')

ax2 = ax.twinx()
ax2.plot(climate_change.index, climate_change["relative_temp"], color='red')
ax2.set_ylabel('Relative temperature (Celsius)', color='red')
plt.show()

fig, ax = plt.subplots()
ax.plot(climate_change.index, climate_change["co2"], color='blue')
ax.set_xlabel('Time')
ax.set_ylabel('CO2 (ppm)', color='blue')
ax.tick_params('y', colors='blue')

ax2 = ax.twinx()
ax2.plot(climate_change.index, climate_change["relative_temp"], color='red')
ax2.set_ylabel('Relative temperature (Celsius)', color='red')
ax2.tick_params('y', colors='red')
plt.show()
fig, ax = plt.subplots()
plot_timeseries(ax, climate_change.index, climate_change['co2'],
'blue', 'Time', 'CO2 (ppm)')
ax2 = ax.twinx()
plot_timeseries(ax2, climate_change.index, climate_change['relative_temp'],
'red', 'Time', 'Relative temperature (Celsius)')
ax2.annotate(">1 degree", xy=(pd.Timestamp("2015-10-06"), 1))
plt.show()

ax2.annotate(">1 degree",
xy=(pd.Timestamp('2015-10-06'), 1),
xytext=(pd.Timestamp('2008-10-06'), -0.2),
arrowprops={"arrowstyle":"->", "color":"gray"})

def plot_timeseries(axes, x, y, color, xlabel, ylabel):

axes.plot(x, y, color=color)
axes.set_xlabel(xlabel)
axes.set_ylabel(ylabel, color=color)
axes.tick_params('y', colors=color)

fig, ax = plt.subplots()
plot_timeseries(ax, climate_change.index, climate_change['co2'],
'blue', 'Time', 'CO2 (ppm)')
ax2 = ax.twinx()
plot_timeseries(ax2, climate_change.index,
climate_change['relative_temp'],
'red', 'Time', 'Relative temperature (Celsius)')
plt.show()

medals = pd.read_csv('medals_by_country_2016.csv', index_col=0)

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
plt.show()
fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
plt.show()

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
ax.bar(medals.index, medals["Silver"], bottom=medals["Gold"])
ax.bar(medals.index, medals["Bronze"], bottom=medals["Gold"] + medals["Silver"])
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
plt.show()

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"], label="Gold")
ax.bar(medals.index, medals["Silver"], bottom=medals["Gold"], label="Silver")
ax.bar(medals.index, medals["Bronze"], bottom=medals["Gold"] + medals["Silver"], label="Bronze")

ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
ax.legend()
plt.show()
fig, ax = plt.subplots()
ax.hist(mens_rowing["Height"])
ax.hist(mens_gymnastics["Height"])
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
plt.show()

ax.hist(mens_rowing["Height"], label="Rowing", bins=5)

ax.hist(mens_gymnastics["Height"], label="Gymnastics", bins=5)
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
ax.legend()
plt.show()

fig, ax = plt.subplots()
ax.scatter(climate_change["co2"], climate_change["relative_temp"])
ax.set_xlabel("CO2 (ppm)")
ax.set_ylabel("Relative temperature (Celsius)")
plt.show()

eighties = climate_change["1980-01-01":"1989-12-31"]
nineties = climate_change["1990-01-01":"1999-12-31"]
fig, ax = plt.subplots()
ax.scatter(eighties["co2"], eighties["relative_temp"], color="red", label="eighties")
ax.scatter(nineties["co2"], nineties["relative_temp"], color="blue", label="nineties")
ax.legend()
ax.set_xlabel("CO2 (ppm)")
ax.set_ylabel("Relative temperature (Celsius)")
plt.show()

fig, ax = plt.subplots()
ax.bar("Rowing", mens_rowing["Height"].mean(), yerr=mens_rowing["Height"].std())
ax.bar("Gymnastics", mens_gymnastics["Height"].mean(), yerr=mens_gymnastics["Height"].std())
ax.set_ylabel("Height (cm)")
plt.show()

fig, ax = plt.subplots()
ax.errorbar(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"],
yerr=seattle_weather["MLY-TAVG-STDDEV"])
ax.errorbar(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"],
yerr=austin_weather["MLY-TAVG-STDDEV"])
ax.set_ylabel("Temperature (Fahrenheit)")
plt.show()

fig, ax = plt.subplots()
ax.boxplot([mens_rowing["Height"], mens_gymnastics["Height"]])
ax.set_xticklabels(["Rowing", "Gymnastics"])
ax.set_ylabel("Height (cm)")
plt.show()

## Introduction to Data Visualization with Matplotlib

### Preparing Your Figures to Share

#### Changing Plot Style

To change the plot style in Matplotlib, you can use the following code:
```python
import matplotlib.pyplot as plt
fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])
ax.plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
ax.set_xlabel("Time (months)")
ax.set_ylabel("Average temperature (Fahrenheit degrees)")
plt.show()

plt.style.use()

plt.style.use("ggplot")
fig, ax = plt.subplots()
ax.plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])
ax.plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
ax.set_xlabel("Time (months)")
ax.set_ylabel("Average temperature (Fahrenheit degrees)")
plt.show()

plt.style.use("default")

plt.style.use("bmh")
plt.style.use("seaborn-colorblind")

fig, ax = plt.subplots()
ax.bar(medals.index, medals["Gold"])
ax.set_xticklabels(medals.index, rotation=90)
ax.set_ylabel("Number of medals")
plt.show()

fig.savefig("gold_medals.png")

ls
fig.savefig("gold_medals.jpg")
fig.savefig("gold_medals.jpg", quality=50)
fig.savefig("gold_medals.svg")

fig.savefig("gold_medals.png", dpi=300)

fig.set_size_inches([5, 3])

fig.set_size_inches([3, 5])

sports = summer_2016_medals["Sport"].unique()
print(sports)

fig, ax = plt.subplots()
for sport in sports:
sport_df = summer_2016_medals[summer_2016_medals["Sport"] == sport]
ax.bar(sport, sport_df["Height"].mean(), yerr=sport_df["Height"].std())
ax.set_ylabel("Height (cm)")
ax.set_xticklabels(sports, rotation=90)
plt.show()

seaborn.relplot(x="horsepower", y="mpg", hue="origin", size="weight",

sizes=(40, 400), alpha=.5, palette="muted",
height=6, data=mpg)
 unique

sport

sport_d_f

bar
unique

unique_sports = df['Sport'].unique()
 sport

sport_df sport

bar

sport

sport_df['Height'].mean()

sport_df['Height'].std()