matplotlib.txt

import matplotlib.pyplot as plt


df = pd.read_sql(query, connection)
print(df.head(5))

amounts=df.groupby(['Year','Category'])['Amount'].sum().tolist()
years=df.groupby(['Year','Category'])['Year'].min().tolist()

print(amounts)
print(years)
plt.clf()
fig, ax = plt.subplots()
ax.scatter(years,amounts)
plt.show()


>>customize
ax.plot(x,y,
marker="o"
or
marker="v",

linestyle="--" #means dashed
linestyle="none" #no lines
color="r" #line color is red
)

ax.set_xlabel("Time (months)")

ax.set_ylabel("Average temperature")
ax.set_title("Weather in Seattle")


>>line style

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

# Plot Austin data, setting data appearance
ax.plot(austin_weather["MONTH"], austin_weather["MLY-PRCP-NORMAL"], color='b',marker='v',linestyle='--')

# Call show to display the resulting plot
plt.show()


>>Small multiples

fig, ax= plt.subplots(3,2)  #three rows of subplots and two columns

ax[0,0].plot(seattle_weather['month'], seattle_weather['mly-prcp-normal'],color='b')


>>special case
fig, ax=plt.subplots(2,1)

ax[0].plot(...)
ax[1].plot(...)

ax[1].set_xlabel applies to both index=0 and index=1

sharey=True means the both subplots will have the same number of y elements

# Create a Figure and an array of subplots with 2 rows and 2 columns
fig, ax = plt.subplots(2, 2)

# Addressing the top left Axes as index 0, 0, plot month and Seattle precipitation
ax[0, 0].plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"])

# In the top right (index 0,1), plot month and Seattle temperatures
ax[0, 1].plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"])

# In the bottom left (1, 0) plot month and Austin precipitations
ax[1, 0].plot(austin_weather["MONTH"], austin_weather["MLY-PRCP-NORMAL"])

# In the bottom right (1, 1) plot month and Austin temperatures
ax[1, 1].plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"])
plt.show()


>>guides

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

# Plot Seattle precipitation data in the top axes
ax[0].plot(seattle_weather['MONTH'], seattle_weather['MLY-PRCP-NORMAL'], color = 'r')
ax[0].plot(seattle_weather['MONTH'], seattle_weather['MLY-PRCP-25PCTL'], color = 'r', linestyle = '--')
ax[0].plot(seattle_weather['MONTH'], seattle_weather['MLY-PRCP-75PCTL'], color = 'r', linestyle = '--')

# Plot Austin precipitation data in the bottom axes
ax[1].plot(austin_weather['MONTH'], austin_weather['MLY-PRCP-NORMAL'], color = 'b')
ax[1].plot(austin_weather['MONTH'], austin_weather['MLY-PRCP-25PCTL'], color = 'b', linestyle = '--')
ax[1].plot(austin_weather['MONTH'], austin_weather['MLY-PRCP-75PCTL'], color = 'b', linestyle = '--')

plt.show()

>>time series data


climate_change.index

climate_change['relative_temp']  #variation for the 10 year average temperature
climate_change['co2']

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']


>>
# Import pandas as pd
import pandas as pd

# Read the data from file using read_csv
climate_change = pd.read_csv('climate_change.csv', parse_dates=True, index_col='date')

print(climate_change.head(5))

>>

import matplotlib.pyplot as plt

# Use plt.subplots to create fig and ax
fig, ax= plt.subplots()

# Create variable seventies with data from "1970-01-01" to "1979-12-31"
seventies = climate_change["1970-01-01" : "1979-12-31"]

# Add the time-series for "co2" data from seventies to the plot
ax.plot(seventies.index, seventies["co2"])

plt.show()

>> creating a twin axis - both share the same x axis

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

ax2=ax.twinx()
ax2.plot(climate_change.index, climate_change['relative_temp'], color=red)
ax2.set_ylabel('relative temp(celsius)')
ax2.tick_params('y',colors='red')
plt.show()

>>create a function

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

  # Plot the inputs x,y in the provided color
  axes.plot(x, y, color=color)

  # Set the x-axis label
  axes.set_xlabel(xlabel)

  # Set the y-axis label
  axes.set_ylabel(ylabel, color=color)

>>calling the function
plot_timeseries(ax,climate_change.index,climate_change['co2'], "blue", "Time (years)", "CO2 levels")

# Create a twin Axes object that shares the x-axis
ax2 = ax.twinx()

# Plot the relative temperature data in red
plot_timeseries(ax,climate_change.index,climate_change['relative_temp'], "red", "Time (years)","Relative temperature (Celsius)")
plt.show()


>>>Annotation

ax2.annotate(">1 degree", xy=[pd.TimeStamp('2015-10-09'),1]

or

ax2.annotate(">1 degree", xy=(pd.TimeStamp('2015-10-09'),1),
xytext=(pd.Timestamp('2008-10-06'),-02)
arrowprops={}
)

or arrowprops={"arrowstyle":"->","color":"gray"}


fig, ax = plt.subplots()

fig, ax = plt.subplots()

# Plot the CO2 levels time-series in blue
plot_timeseries(ax, climate_change.index, climate_change["co2"], 'blue', "Time (years)", "CO2 levels")

# Create an Axes object that shares the x-axis
ax2 = ax.twinx()

# Plot the relative temperature data in red
plot_timeseries(ax2, climate_change.index, climate_change['relative_temp'], 'red', "Time (years)", "Relative temp (Celsius)")

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

plt.show()


>>Bar

fig, ax = plt.subplots()

# Plot a bar-chart of gold medals as a function of country
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'])
# Set the x-axis tick labels to the country names
ax.set_xticklabels(medals.index, rotation=90)

# Set the y-axis label
ax.set_ylabel('Number of medals')

plt.show()

>>Add labels

# Add bars for "Gold" with the label "Gold"
ax.bar(medals.index,medals["Gold"],label="Gold")

# Stack bars for "Silver" on top with label "Silver"
ax.bar(medals.index,medals['Silver'],bottom=medals['Gold'], label="Silver")

# Stack bars for "Bronze" on top of that with label "Bronze"
ax.bar(medals.index,medals['Bronze'],bottom=medals['Gold']+medals['Silver'],label="Bronze")
# Display the legend
ax.legend()

plt.show()


>>histogram
fig, ax = plt.subplots()

ax.hist(mens_rowing["Height"], label="Rowing", bins=5)
ax.hist(mens_gymnastic["Height], label="Gymnastics", bins=5)
#ax.hist(mens_gymnastic["Height], label="Gymnastics", bins=[150,160,170,180,190,200,210], histtype=step)
ax.set_xlabel("Height (cm)")
ax.set_ylabel("# of observations")
plt.legend()
plt.show()


fig, ax = plt.subplots()

# Plot a histogram of "Weight" for mens_rowing
ax.hist(mens_rowing['Weight'],label="Rowing", histtype='step',bins=5)

# Compare to histogram of "Weight" for mens_gymnastics
ax.hist(mens_gymnastics['Weight'],label="Gymnastics", histtype='step',bins=5)

ax.set_xlabel("Weight (kg)")
ax.set_ylabel("# of observations")

# Add the legend and show the Figure
plt.legend()
plt.show()


>>Statistical plotting

ax.bar("Rowing",
	mens_rowing["Height"].mean(),
	yerr=mens_rowing["Height"].std())


ax.errorbar(seattle_weather["MONTH"],
	seattle_weather["MLY-TAVG-NORMAL"],
	seattle_weather["MLY-TAVG-STDDEV"])

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

plt.show()

#intercordal range are the edges of the boxes
25% and 75% percentiles
whiskers are 1.5 times the intercordial range
points outside the whiskers are outliers

>>>

fig, ax = plt.subplots()

# Add a bar for the rowing "Height" column mean/std
ax.bar("Rowing", mens_rowing['Height'].mean(), yerr=mens_rowing['Height'].std())

# Add a bar for the gymnastics "Height" column mean/std
ax.bar("Rowing", mens_gymnastics['Height'].mean(), yerr=mens_gymnastics['Height'].std())

# Label the y-axis
ax.set_ylabel("Height (cm)")

>>>

fig, ax = plt.subplots()

# Add Seattle temperature data in each month with error bars
ax.errorbar(seattle_weather["MONTH"],
	seattle_weather["MLY-TAVG-NORMAL"],
	seattle_weather["MLY-TAVG-STDDEV"])

# Add Austin temperature data in each month with error bars
ax.errorbar(austin_weather["MONTH"],
	austin_weather["MLY-TAVG-NORMAL"],
	austin_weather["MLY-TAVG-STDDEV"])

# Set the y-axis label
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()

>>>
bivariant comparison


fig, ax = plt.subplots()

# Add data: "co2" on x-axis, "relative_temp" on y-axis
ax.scatter(climate_change['co2'],climate_change['relative_temp'], color='red', label="co2"
,c=climate_change.index  #older dates will be a darker color
)

ax.set_xlabel('CO2 (ppm)')
ax.set_ylabel('Relative temperature (Celsius)')

plt.show()

plt.style.use('ggplot')
plt.style.use('bmh')
plt.style.use('seaborn-blind')
plt.style.use('Solarize_Light2')

dark backgrounds are less visible
tableau-colorblind10
grayscale

one out of twenty people are color blind

>>Saving the figure

fig.savefig('gold_medals.png')

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

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

fig.set_size_inches([5,3]) #width and height of the figure

programming make your faster

summer_2016_medals['Sport']

sports= summer_2016_medals['Sport'].unique()  # a column is a series

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()



>>
import matplotlib.pyplot as plt

1) pyplot can accept arrays or list

plt.plot(months,prices,color='red', linestyle='--')
plt.plot(months,prices_new, color='green', linestyle='--')

- solid line
-- dashed line
-. dashed dot line
: dotted

xlabel
ylabel
title

plt.show()

>>scatter
plt.scatter(x=months, y=prices, color=red)

>>Histograms

1) Is your data skewed
2) Is your data centered around the average
3) Do you have abnormal data points(outliers) in your data

plt.hist(x=prices, bins=3)
plt.show()

plt.hist(x=prices, bins=6,normed=1)  #the number of observations decrease per bin as the number of bins increase

normalization shows the percentage of observations rather than the frequency counts


# Plot histogram of stocks_A
plt.hist(stock_A, bins=100, alpha=0.4)

# Plot histogram of stocks_B 
plt.hist(stock_B, bins=100, alpha=0.4)

# Display plot
plt.show()