matplotlib_plots.py

df_can.sort_values(['Total'], ascending=False, axis=0, inplace=True)

# get the top 5 entries
df_top5 = df_can.head()

# transpose the dataframe
df_top5 = df_top5[years].transpose()

df_top5.head()

df_top5.index = df_top5.index.map(int)
df_top5.plot(kind='area',
             stacked=False,
             figsize=(20, 10))  # pass a tuple (x, y) size

plt.title('Immigration Trend of Top 5 Countries')
plt.ylabel('Number of Immigrants')
plt.xlabel('Years')

plt.show()








# Artist Layer

df_least5 = df_can.tail(5)
     
    # transpose the dataframe
df_least5 = df_least5[years].transpose() 
df_least5.head()

df_least5.index = df_least5.index.map(int) # let's change the index values of df_least5 to type integer for plotting
ax=df_least5.plot(kind='area', alpha=0.45, figsize=(20, 10)) 

ax.set_title('Immigration Trend of 5 Countries with Least Contribution to Immigration')
ax.set_ylabel('Number of Immigrants')
ax.set_xlabel('Years'
              
  
              
              
              
              
              
# 'bin_edges' is a list of bin intervals
count, bin_edges = np.histogram(df_can['2013'])

df_can['2013'].plot(kind='hist', figsize=(8, 5), xticks=bin_edges)

plt.title('Histogram of Immigration from 195 countries in 2013') # add a title to the histogram
plt.ylabel('Number of Countries') # add y-label
plt.xlabel('Number of Immigrants') # add x-label

plt.show()
              
              
              
              
              
              
              
              
              
              
              
              
              
              
 df_iceland.plot(kind='bar', figsize=(10, 6), rot=90)  # rotate the xticks(labelled points on x-axis) by 90 degrees

plt.xlabel('Year')
plt.ylabel('Number of Immigrants')
plt.title('Icelandic Immigrants to Canada from 1980 to 2013')

# Annotate arrow
plt.annotate('',  # s: str. Will leave it blank for no text
             xy=(32, 70),  # place head of the arrow at point (year 2012 , pop 70)
             xytext=(28, 20),  # place base of the arrow at point (year 2008 , pop 20)
             xycoords='data',  # will use the coordinate system of the object being annotated
             arrowprops=dict(arrowstyle='->', connectionstyle='arc3', color='blue', lw=2)
             )

plt.show()     
              
              
              
              
df_iceland.plot(kind='bar', figsize=(10, 6), rot=90)

plt.xlabel('Year')
plt.ylabel('Number of Immigrants')
plt.title('Icelandic Immigrants to Canada from 1980 to 2013')

# Annotate arrow
plt.annotate('',  # s: str. will leave it blank for no text
             xy=(32, 70),  # place head of the arrow at point (year 2012 , pop 70)
             xytext=(28, 20),  # place base of the arrow at point (year 2008 , pop 20)
             xycoords='data',  # will use the coordinate system of the object being annotated
             arrowprops=dict(arrowstyle='->', connectionstyle='arc3', color='blue', lw=2)
             )

# Annotate Text
plt.annotate('2008 - 2011 Financial Crisis',  # text to display
             xy=(28, 30),  # start the text at at point (year 2008 , pop 30)
             rotation=72.5,  # based on trial and error to match the arrow
             va='bottom',  # want the text to be vertically 'bottom' aligned
             ha='left',  # want the text to be horizontally 'left' algned.
             )

plt.show()
              
df_top15.plot(kind='barh', figsize=(12, 12), color='steelblue')
plt.xlabel('Number of Immigrants')
plt.title('Top 15 Conuntries Contributing to the Immigration to Canada between 1980 - 2013')

    # annotate value labels to each country
for index, value in enumerate(df_top15): 
     label = format(int(value), ',') # format int with commas
    
    # place text at the end of bar (subtracting 47000 from x, and 0.1 from y to make it fit within the bar)
plt.annotate(label, xy=(value - 47000, index - 0.10), color='white')

plt.show()
              
              
              
              
  colors_list = ['gold', 'yellowgreen', 'lightcoral', 'lightskyblue', 'lightgreen', 'pink']
explode_list = [0.1, 0, 0, 0, 0.1, 0.1] # ratio for each continent with which to offset each wedge.

df_continents['Total'].plot(kind='pie',
                            figsize=(10, 6),
                            autopct='%1.1f%%', 
                            startangle=90,    
                            shadow=True,       
                            labels=None,         # turn off labels on pie chart
                            pctdistance=1.12,    # the ratio between the center of each pie slice and the start of the text generated by autopct 
                            #colors=colors_list,  # add custom colors
                            #explode=explode_list # 'explode' lowest 3 continents
                            )

# scale the title up by 12% to match pctdistance
plt.title('Immigration to Canada by Continent [1980 - 2013]', y=1.12, fontsize = 15) 

plt.axis('equal') 

# add legend
plt.legend(labels=df_continents.index, loc='upper left', fontsize=7) 

plt.show()
              
              
              
 df_japan.plot(kind='box', figsize=(8, 6))

plt.title('Box plot of Japanese Immigrants from 1980 - 2013')
plt.ylabel('Number of Immigrants')

plt.show()             
              
              
              
              
              
#sub plots
              
              fig = plt.figure() # create figure

ax0 = fig.add_subplot(1, 2, 1) # add subplot 1 (1 row, 2 columns, first plot)
ax1 = fig.add_subplot(1, 2, 2) # add subplot 2 (1 row, 2 columns, second plot). See tip below**

# Subplot 1: Box plot
df_china.plot(kind='box', color='blue', vert=False, figsize=(20, 6), ax=ax0) # add to subplot 1
ax0.set_title('Box Plots of Immigrants from China and India (1980 - 2013)')
ax0.set_xlabel('Number of Immigrants')
ax0.set_ylabel('Countries')

# Subplot 2: Line plot
df_china.plot(kind='line', figsize=(20, 6), ax=ax1) # add to subplot 2
ax1.set_title ('Line Plots of Immigrants from China and India (1980 - 2013)')
ax1.set_ylabel('Number of Immigrants')
ax1.set_xlabel('Years')

plt.show()
              
              
              
              
              
              
              
              
              
              
              
              
              
              
              
              
              
              
              
              

#bubble

df_can_t = df_can[years].transpose()

# cast the Years (the index) to type int
df_can_t.index = map(int, df_can_t.index)

# let's label the index. This will automatically be the column name when we reset the index
df_can_t.index.name = 'Year'

# reset index to bring the Year in as a column
df_can_t.reset_index(inplace=True)

# view the changes
df_can_t.head()


# normalize Brazil data
norm_brazil = (df_can_t['Brazil'] - df_can_t['Brazil'].min()) / (df_can_t['Brazil'].max() - df_can_t['Brazil'].min())

# normalize Argentina data
norm_argentina = (df_can_t['Argentina'] - df_can_t['Argentina'].min()) / (df_can_t['Argentina'].max() - df_can_t['Argentina'].min())

# Brazil
ax0 = df_can_t.plot(kind='scatter',
                    x='Year',
                    y='Brazil',
                    figsize=(14, 8),
                    alpha=0.5,  # transparency
                    color='green',
                    s=norm_brazil * 2000 + 10,  # pass in weights 
                    xlim=(1975, 2015)
                    )

# Argentina
ax1 = df_can_t.plot(kind='scatter',
                    x='Year',
                    y='Argentina',
                    alpha=0.5,
                    color="blue",
                    s=norm_argentina * 2000 + 10,
                    ax=ax0
                    )

ax0.set_ylabel('Number of Immigrants')
ax0.set_title('Immigration from Brazil and Argentina from 1980 to 2013')
ax0.legend(['Brazil', 'Argentina'], loc='upper left', fontsize='x-large')