Related
I need help creating subplots in matplotlib dynamically from a pandas dataframe.
The data I am using is from data.word.
I have already created the viz but the plots have been created manually.
The reason why I need it dynamically is because I am going to apply a filter dynamically (in Power BI) and i need the graph to adjust to the filter.
This is what i have so far:
I imported the data and got it in the shape i need:
import matplotlib.pyplot as plt
import pandas as pd
import numpy as
# read file from makeover monday year 2018 week 48
df = pd.read_csv(r'C:\Users\Ruth Pozuelo\Documents\python_examples\data\2018w48.csv', usecols=["city", "category","item", "cost"], index_col=False, decimal=",")
df.head()
this is the table:
I then apply the filter that will come from Power BI dynamically:
df = df[df.category=='Party night']
and then I count the number of plots based on the number of items I get after I apply the filter:
itemCount = df['item'].nunique() #number of plots
If I then plot the subplots:
fig, ax = plt.subplots( nrows=1, ncols=itemCount ,figsize=(30,10), sharey=True)
I get the skeleton:
So far so good!
But now i am suck on how to feed the x axis to the loop to generate the subcategories. I am trying something like below, but nothing works.
#for i, ax in enumerate(axes.flatten()):
# ax.plot(??,cityValues, marker='o',markersize=25, lw=0, color="green") # The top-left axes
As I already have the code for the look and feel of the chart, annotations,ect, I would love to be able to use the plt.subplots method and I prefer not use seaborn if possible.
Any ideas on how to get his working?
Thanks in advance!
The data was presented to us and we used it as the basis for our code. I prepared a list of columns and a list of coloring and looped through them. axes.rabel() is more memory efficient than axes.fatten(). This is because the list contains an object for each subplot, allowing for centralized configuration.
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
url='https://raw.githubusercontent.com/Curbal-Data-Labs/Matplotlib-Labs/master/2018w48.csv'
dataset = pd.read_csv(url)
dataset.drop_duplicates(['city','item'], inplace=True)
dataset.pivot_table(index='city', columns='item', values='cost', aggfunc='sum', margins = True).sort_values('All', ascending=True).drop('All', axis=1)
df = dataset.pivot_table(index='city', columns='item', values='cost', aggfunc='sum', margins = True).sort_values('All', ascending=True).drop('All', axis=1).sort_values('All', ascending=False, axis=1).drop('All').reset_index()
# comma replace
for c in df.columns[1:]:
df[c] = df[c].str.replace(',','.').astype(float)
fig, axes = plt.subplots(nrows=1, ncols=5, figsize=(30,10), sharey=True)
colors = ['green','blue','red','black','brown']
col_names = ['Dinner','Drinks at Dinner','2 Longdrinks','Club entry','Cinema entry']
for i, (ax,col,c) in enumerate(zip(axes.ravel(), col_names, colors)):
ax.plot(df.loc[:,col], df['city'], marker='o', markersize=25, lw=0, color=c)
ax.set_title(col)
for i,j in zip(df[col], df['city']):
ax.annotate('$'+str(i), xy=(i, j), xytext=(i-4,j), color="white", fontsize=8)
ax.set_xticks([])
ax.spines[['top', 'right', 'left', 'bottom']].set_visible(False)
ax.grid(True, axis='y', linestyle='solid', linewidth=2)
ax.grid(True, axis='x', linestyle='solid', linewidth=0.2)
ax.xaxis.tick_top()
ax.xaxis.set_label_position('top')
ax.set_xlim(xmin=0, xmax=160)
ax.xaxis.set_major_formatter('${x:1.0f}')
ax.tick_params(labelsize=8, top=False, left=False)
plt.show()
Working Example below. I used seaborn to plot the bars but the idea is the same you can loop through the facets and increase a count. Starting from -1 so that your first count = 0, and use this as the axis label.
import seaborn as sns
fig, ax = plt.subplots( nrows=1, ncols=itemCount ,figsize=(30,10), sharey=True)
df['Cost'] = df['Cost'].astype(float)
count = -1
variables = df['Item'].unique()
fig, axs = plt.subplots(1,itemCount , figsize=(25,70), sharex=False, sharey= False)
for var in variables:
count += 1
sns.barplot(ax=axs[count],data=df, x='Cost', y='City')
My data is in a dataframe of two columns: y and x. The data refers to the past few years. Dummy data is below:
np.random.seed(167)
rng = pd.date_range('2017-04-03', periods=365*3)
df = pd.DataFrame(
{"y": np.cumsum([np.random.uniform(-0.01, 0.01) for _ in range(365*3)]),
"x": np.cumsum([np.random.uniform(-0.01, 0.01) for _ in range(365*3)])
}, index=rng
)
In first attempt, I plotted a scatterplot with Seaborn using the following code:
import seaborn as sns
import matplotlib.pyplot as plt
def plot_scatter(data, title, figsize):
fig, ax = plt.subplots(figsize=figsize)
ax.set_title(title)
sns.scatterplot(data=data,
x=data['x'],
y=data['y'])
plot_scatter(data=df, title='dummy title', figsize=(10,7))
However, I would like to generate a 4x3 matrix including 12 scatterplots, one for each month with year as hue. I thought I could create a third column in my dataframe that tells me the year and I tried the following:
import seaborn as sns
import matplotlib.pyplot as plt
def plot_scatter(data, title, figsize):
fig, ax = plt.subplots(figsize=figsize)
ax.set_title(title)
sns.scatterplot(data=data,
x=data['x'],
y=data['y'],
hue=data.iloc[:, 2])
df['year'] = df.index.year
plot_scatter(data=df, title='dummy title', figsize=(10,7))
While this allows me to see the years, it still shows all the data in the same scatterplot instead of creating multiple scatterplots, one for each month, so it's not offering the level of detail I need.
I could slice the data by month and build a for loop that plots one scatterplot per month but I actually want a matrix where all the scatterplots use similar axis scales. Does anyone know an efficient way to achieve that?
To create multiple subplots at once, seaborn introduces figure-level functions. The col= argument indicates which column of the dataframe should be used to identify the subplots. col_wrap= can be used to tell how many subplots go next to each other before starting an additional row.
Note that you shouldn't create a figure, as the function creates its own new figure. It uses the height= and aspect= arguments to tell the size of the individual subplots.
The code below uses a sns.relplot() on the months. An extra column for the months is created; it is made categorical to fix an order.
To remove the month= in the title, you can loop through the generated axes (a recent seaborn version is needed for axes_dict). With sns.set(font_scale=...) you can change the default sizes of all texts.
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
np.random.seed(167)
dates = pd.date_range('2017-04-03', periods=365 * 3, freq='D')
df = pd.DataFrame({"y": np.cumsum([np.random.uniform(-0.01, 0.01) for _ in range(365 * 3)]),
"x": np.cumsum([np.random.uniform(-0.01, 0.01) for _ in range(365 * 3)])
}, index=dates)
df['year'] = df.index.year
month_names = pd.date_range('2017-01-01', periods=12, freq='M').strftime('%B')
df['month'] = pd.Categorical.from_codes(df.index.month - 1, month_names)
sns.set(font_scale=1.7)
g = sns.relplot(kind='scatter', data=df, x='x', y='y', hue='year', col='month', col_wrap=4, height=4, aspect=1)
# optionally remove the `month=` in the title
for name, ax in g.axes_dict.items():
ax.set_title(name)
plt.setp(g.axes, xlabel='', ylabel='') # remove all x and y labels
g.axes[-2].set_xlabel('x', loc='left') # set an x label at the left of the second to last subplot
g.axes[4].set_ylabel('y') # set a y label to 5th subplot
plt.subplots_adjust(left=0.06, bottom=0.06) # set some more spacing at the left and bottom
plt.show()
I am trying to plot a simple .csv file downloaded from Yahoo-finance (file example here), but I cannot understand why the years appear as (apparently) random numbers. Please see image below:
Another thing that I would like to do is to remove the x axis from the top graph (since the same axis is already in the bottom plot) but I would like to keep the dashed grid. I tired to use ax[0].set_xticklabels([]), but it didn't work.
Here is my code:
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.dates import DateFormatter, MonthLocator, YearLocator
#LOAD DATA
df_name = "0P0000UL8U.L.csv"
col_list = ["Date", "Adj Close"] #list of column to import
df = pd.read_csv(df_name, header=0, usecols=col_list, na_values=['null'], thousands=r',', parse_dates=["Date"], dayfirst=True)
df = df.dropna() #Drop the rows where at least one element is missing.
df.set_index("Date", inplace = True)
df.index = [pd.to_datetime(date).date() for date in df.index] #convert index to datetime.date, not datetime.datetime.
print("Opening df:\n", df)
print("\nLength of df: ", len(df.index))
#PLOT DATA
fig, ax = plt.subplots(2,1, figsize=(11,5))
plt.subplots_adjust(left=None, bottom=None, right=None, top=None, wspace=0.25, hspace=0.8) #Adjust space between graphs
df[["Adj Close"]].plot(ax=ax[0], kind="line", style="-", color="blue", stacked=False, rot=90)
ax[0].set_axisbelow(True) # To put plot grid below plots
ax[0].yaxis.grid(color='gray', linestyle='dashed')
ax[0].xaxis.grid(color='gray', linestyle='dashed')
ax[0].xaxis.set_major_locator(YearLocator()) # specify a MonthLocator
ax[0].xaxis.set_major_formatter(DateFormatter("%b %Y"))
ax[0].set(xlabel=None, ylabel="Price") # Set title and labels for axes
df[["Adj Close"]].plot(ax=ax[1], kind="line", style="-", color="blue", stacked=False, rot=90)
ax[1].set_axisbelow(True) # To put plot grid below plots
ax[1].yaxis.grid(color='gray', linestyle='dashed')
ax[1].xaxis.grid(color='gray', linestyle='dashed')
ax[1].xaxis.set_major_locator(YearLocator()) # specify a MonthLocator
ax[1].xaxis.set_major_formatter(DateFormatter("%b %Y"))
ax[1].set(xlabel="Time", ylabel="Price") # Set title and labels for axes
fig.savefig("0P0000UL8U.L.png", bbox_inches='tight', dpi=300)
What am I doing wrong? Thank for any help in advance.
To remove the x-Axis labels from the top graph, you can add the following line:
ax[0].tick_params(labelbottom=False)
before ax[0].set(xlabel=None, ylabel="Price")
It's not your fault. Python 3 is very far from stable yet. That's why hardcore developers still prefer Python 2. This time matplotlib devs screwed dates handling. They even have a number of corresponding bugs (#18010, #17983, #34850).
Meantime you can downgrade matplotlib to v 3.2.2, it's working perfectly and wait if devs repair the bug.
I am trying to create a countplot with a lineplot over it as practice for some data visualisation I will be doing in work. I am looking at the kickstarter data on kaggle Link here
I run a countplot with a hue on the state of the project (successful, failed, canceled) and both of these are ordered
filter_list = ['failed', 'successful', 'canceled']
df2 = df[df.state.isin(filter_list)]
fig = plt.gcf()
fig.set_size_inches( 16, 10)
sns.countplot(x='main_category', hue='state', data=df2, order = df2['main_category'].value_counts().index,
hue_order = df2['state'].value_counts().index)
This comes out as follows:
I then create my second axis and add a lineplot
fig, ax = plt.subplots()
fig.set_size_inches( 16, 10)
ax = sns.countplot(x='main_category', hue='state', data=df, ax=ax, order = df2['main_category'].value_counts().index,
hue_order = df2['state'].value_counts().index)
ax2 = ax.twinx()
sns.lineplot(x='main_category', y='backers', data=df2, ax =ax2)
But this changes the column labels as seen below:
It appears that the data is the same its just the order of columns is different. I am still learning so my code may be inefficent or some of it redundant but any help would be appreciated. The only other things are how df is created which is as follows:
import pandas as pd
import numpy as np
import seaborn as sns; sns.set(style="white", color_codes=True)
import matplotlib.pyplot as plt
df = pd.read_csv('ks.csv')
df = df.drop(['ID'], axis = 1)
df.head()
I don't think lineplot is what you are looking for. lineplot is supposed to be used with numeric data, not categorical. I'm even surprised this worked at all.
I think you are looking for pointplot instead
filter_list = ['failed', 'successful', 'canceled']
df2 = df[df.state.isin(filter_list)]
order = df2['main_category'].value_counts().index
fig = plt.figure()
ax1 = sns.countplot(x='main_category', hue='state', data=df2, order=order,
hue_order=filter_list)
ax2 = ax1.twinx()
sns.pointplot(x='main_category', y='backers', data=df2, ax=ax2, order=order)
Note that used like that, pointplot will show the average number of backers across categories. If that's not what you want, you can pass another aggregation function using the estimator= paramater
eg
sns.pointplot(x='main_category', y='backers', data=df2, ax=ax2, order=order, estimator=np.sum)
I am trying to do analysis on a bike share dataset. Part of the analysis includes showing the weekends' demand in date wise plot.
My dataframe in pandas with last 5 row looks like this.
Here is my code for date vs total ride plot.
import seaborn as sns
sns.set_style("darkgrid")
plt.plot(d17_day_count)
plt.show()
.
I want to highlight weekends in the plot. So that it could look something similar to this plot.
I am using Python with matplotlib and seaborn library.
You can easily highlight areas by using axvspan, to get the areas to be highlighted you can run through the index of your dataframe and search for the weekend days. I've also added an example for highlighting 'occupied hours' during a working week (hopefully that doesn't confuse things).
I've created dummy data for a dataframe based on days and another one for hours.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# dummy data (Days)
dates_d = pd.date_range('2017-01-01', '2017-02-01', freq='D')
df = pd.DataFrame(np.random.randint(1, 20, (dates_d.shape[0], 1)))
df.index = dates_d
# dummy data (Hours)
dates_h = pd.date_range('2017-01-01', '2017-02-01', freq='H')
df_h = pd.DataFrame(np.random.randint(1, 20, (dates_h.shape[0], 1)))
df_h.index = dates_h
#two graphs
fig, axes = plt.subplots(nrows=2, ncols=1, sharex=True)
#plot lines
dfs = [df, df_h]
for i, df in enumerate(dfs):
for v in df.columns.tolist():
axes[i].plot(df[v], label=v, color='black', alpha=.5)
def find_weekend_indices(datetime_array):
indices = []
for i in range(len(datetime_array)):
if datetime_array[i].weekday() >= 5:
indices.append(i)
return indices
def find_occupied_hours(datetime_array):
indices = []
for i in range(len(datetime_array)):
if datetime_array[i].weekday() < 5:
if datetime_array[i].hour >= 7 and datetime_array[i].hour <= 19:
indices.append(i)
return indices
def highlight_datetimes(indices, ax):
i = 0
while i < len(indices)-1:
ax.axvspan(df.index[indices[i]], df.index[indices[i] + 1], facecolor='green', edgecolor='none', alpha=.5)
i += 1
#find to be highlighted areas, see functions
weekend_indices = find_weekend_indices(df.index)
occupied_indices = find_occupied_hours(df_h.index)
#highlight areas
highlight_datetimes(weekend_indices, axes[0])
highlight_datetimes(occupied_indices, axes[1])
#formatting..
axes[0].xaxis.grid(b=True, which='major', color='black', linestyle='--', alpha=1) #add xaxis gridlines
axes[1].xaxis.grid(b=True, which='major', color='black', linestyle='--', alpha=1) #add xaxis gridlines
axes[0].set_xlim(min(dates_d), max(dates_d))
axes[0].set_title('Weekend days', fontsize=10)
axes[1].set_title('Occupied hours', fontsize=10)
plt.show()
I tried using the code in the accepted answer but the way the indices are used, the last weekend in the time series does not get highlighted entirely, despite what the image currently shown suggests (this is noticeable mainly with a frequency of 6 hours or more). Also, it does not work if the frequency of the data is higher than daily. This is why I share here a solution that uses the x-axis units so that weekends (or any other recurring time period) can be highlighted without any problem related to the index.
This solution takes only 6 lines of code and it works with any frequency. In the example below, it highlights full weekend days which makes it more efficient than the accepted answer where small frequencies (e.g. 30 minutes) will produce many polygons to cover the whole weekend.
The x-axis limits are used to compute the range of time covered by the plot in terms of days, which is the unit used for matplotlib dates. Then a weekends mask is computed and passed to the where argument of the fill_between plotting function. The masks are processed as right-exclusive so in this case, they must contain Mondays for the highlights to be drawn up to Mondays 00:00. Because plotting these highlights can alter the x-axis limits when weekends occur near the limits, the x-axis limits are set back to the original values after plotting.
Note that contrary to axvspan, the fill_between function needs the y1 and y2 arguments. For some reason, using the default y-axis limits leaves a small gap between the plot frame and the tops and bottoms of the weekend highlights. This issue is solved by running ax.set_ylim(*ax.get_ylim()) just after creating the plot.
import numpy as np # v 1.19.2
import pandas as pd # v 1.1.3
import matplotlib.pyplot as plt # v 3.3.2
import matplotlib.dates as mdates
# Create sample dataset
rng = np.random.default_rng(seed=1234) # random number generator
dti = pd.date_range('2017-01-01', '2017-05-15', freq='D')
counts = 5000 + np.cumsum(rng.integers(-1000, 1000, size=dti.size))
df = pd.DataFrame(dict(Counts=counts), index=dti)
# Draw pandas plot: x_compat=True converts the pandas x-axis units to matplotlib
# date units (not strictly necessary when using a daily frequency like here)
ax = df.plot(x_compat=True, figsize=(10, 5), legend=None, ylabel='Counts')
ax.set_ylim(*ax.get_ylim()) # reset y limits to display highlights without gaps
# Highlight weekends based on the x-axis units
xmin, xmax = ax.get_xlim()
days = np.arange(np.floor(xmin), np.ceil(xmax)+2)
weekends = [(dt.weekday()>=5)|(dt.weekday()==0) for dt in mdates.num2date(days)]
ax.fill_between(days, *ax.get_ylim(), where=weekends, facecolor='k', alpha=.1)
ax.set_xlim(xmin, xmax) # set limits back to default values
# Create appropriate ticks using matplotlib date tick locators and formatters
ax.xaxis.set_major_locator(mdates.MonthLocator())
ax.xaxis.set_minor_locator(mdates.MonthLocator(bymonthday=np.arange(5, 31, step=7)))
ax.xaxis.set_major_formatter(mdates.DateFormatter('\n%b'))
ax.xaxis.set_minor_formatter(mdates.DateFormatter('%d'))
# Additional formatting
ax.figure.autofmt_xdate(rotation=0, ha='center')
title = 'Daily count of trips with weekends highlighted from SAT 00:00 to MON 00:00'
ax.set_title(title, pad=20, fontsize=14);
As you can see, the weekends are always highlighted to the full extent, regardless of where the data starts and ends.
You can find more examples of this solution in the answers I have posted here and here.
I have another suggestion to make in this regard, which takes inspirations from previous posts by other contributors. The code is as follows:
import datetime
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
rng = np.random.default_rng(seed=42) # random number generator
dti = pd.date_range('2021-08-01', '2021-08-31', freq='D')
counts = 5000 + np.cumsum(rng.integers(-1000, 1000, size=dti.size))
df = pd.DataFrame(dict(Counts=counts), index=dti)
weekends = [d for d in df.index if d.isoweekday() in [6,7]]
weekend_list = []
for weekendday in weekends:
d1 = weekendday
d2 = weekendday + datetime.timedelta(days=1)
weekend_list.append((d1, d2))
weekend_df = pd.DataFrame(weekend_list)
sns.set()
plt.figure(figsize=(15, 10), dpi=100)
df.plot()
plt.legend(bbox_to_anchor=(1.02, 0), loc="lower left", borderaxespad=0)
plt.ylabel("Counts")
plt.xlabel("Date of visit")
plt.xticks(rotation = 0)
plt.title("Daily counts of shop visits with weekends highlighted in green")
ax = plt.gca()
for d in weekend_df.index:
print(weekend_df[0][d], weekend_df[1][d])
ax.axvspan(weekend_df[0][d], weekend_df[1][d], facecolor="g", edgecolor="none", alpha=0.5)
ax.relim()
ax.autoscale_view()
plt.savefig("junk.png", dpi=100, bbox_inches='tight', pad_inches=0.2)
The result would be something like the following diagram: