I am having some problems with plotting a Pandas dataframe with repeating range on x-axis after every 17 points. It doesn't start from new line after repetition. How to fix this issue.
import pandas as pd
from matplotlib import pyplot as plt
df = pd.read_excel('BS.xlsx')
plt.plot(df.BZ, df.energy)
plt.show()
Repeating Dataframe
Based on the df provided. You can try as below:
import pandas as pd
from matplotlib import pyplot as plt
df = pd.read_excel('BS.xlsx')
df['range']= df.index//17
ax = plt.axes()
df.groupby('range').apply(lambda x:x.plot(x='BZ', y= 'energy', legend = False, ax=ax))
plt.show()
Related
I want to plot my dataframe (df) as a bar plot based on the time columns, where each bar represents the value counts() for each letter that appears in the column.
Expected output
.
date,00:00:00,01:00:00,02:00:00,03:00:00,04:00:00
2002-02-01,Y,Y,U,N,N
2002-02-02,U,N,N,N,N
2002-02-03,N,N,N,N,N
2002-02-04,N,N,N,N,N
2002-02-05,N,N,N,N,N
When I select individual time columns, I can do as below
import pandas as pd
import numpy as np
from datetime import datetime
import matplotlib.pyplot as plt
df = pd.read_csv('df.csv')
df = df['04:00:00'].value_counts()
df.plot(kind='bar')
plt.show()
How can I plot all the columns on the same bar plot as shown on the expected output.
One possible solution is:
pd.DataFrame({t: df[t].value_counts() for t in df.columns if t != "date"}).T.plot.bar()
Here is an approach via seaborn's catplot:
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
from io import StringIO
df_str = '''date,00:00:00,01:00:00,02:00:00,03:00:00,04:00:00
2002-02-01,Y,Y,U,N,N
2002-02-02,U,N,N,N,N
2002-02-03,N,N,N,N,N
2002-02-04,N,N,N,N,N
2002-02-05,N,N,N,N,N'''
df = pd.read_csv(StringIO(df_str))
df_long = df.set_index('date').melt(var_name='hour', value_name='kind')
g = sns.catplot(kind='count', data=df_long, x='kind', palette='mako',
col='hour', col_wrap=5, height=3, aspect=0.5)
for ax in g.axes.flat:
ax.set_xlabel(ax.get_title()) # use the title as xlabel
ax.grid(True, axis='y')
ax.set_title('')
if len(ax.get_ylabel()) == 0:
sns.despine(ax=ax, left=True) # remove left axis for interior subplots
ax.tick_params(axis='y', size=0)
plt.tight_layout()
plt.show()
I have around 4475 rows of csv data like below:
,Time,Values,Size
0,1900-01-01 23:11:30.368,2,
1,1900-01-01 23:11:30.372,2,
2,1900-01-01 23:11:30.372,2,
3,1900-01-01 23:11:30.372,2,
4,1900-01-01 23:11:30.376,2,
5,1900-01-01 23:11:30.380,,
6,1900-01-01 23:11:30.380,,
7,1900-01-01 23:11:30.380,,
8,1900-01-01 23:11:30.380,,321
9,1900-01-01 23:11:30.380,,111
.
.
4474,1900-01-01 23:11:32.588,,
When I try to create simple seaborn lineplot with below code. It creates line chart but its continuous chart while my data i.e. 'Values' has many empty/nan values which should show as gap on chart. How can I do that?
[from datetime import datetime
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
df = pd.read_csv("Data.csv")
sns.set(rc={'figure.figsize':(13,4)})
ax =sns.lineplot(x="Time", y="Values", data=df)
ax.set(xlabel='Time', ylabel='Values')
plt.xticks(rotation=90)
plt.tight_layout()
plt.show()]
As reported in this answer:
I've looked at the source code and it looks like lineplot drops nans from the DataFrame before plotting. So unfortunately it's not possible to do it properly.
So, the easiest way to do it is to use matplotlib in place of seaborn.
In the code below I generate a dataframe like your with 20% of missing values in 'Values' column and I use matplotlib to draw a plot:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
df = pd.DataFrame({'Time': pd.date_range(start = '1900-01-01 23:11:30', end = '1900-01-01 23:11:30.1', freq = 'L')})
df['Values'] = np.random.randint(low = 2, high = 10, size = len(df))
df['Values'] = df['Values'].mask(np.random.random(df['Values'].shape) < 0.2)
fig, ax = plt.subplots(figsize = (13, 4))
ax.plot(df['Time'], df['Values'])
ax.set(xlabel = 'Time', ylabel = 'Values')
plt.xticks(rotation = 90)
plt.tight_layout()
plt.show()
I have seen many questions on changing the tick frequency on SO, and that did help when I am building a line chart, but I have been struggling when its a bar chart. So below are my codes
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
df = pd.DataFrame(np.random.randint(1,10,(90,1)),columns=['Values'])
df.plot(kind='bar')
plt.show()
and thats the output I see. How do I change the tick frequency ?
(To be more clearer frequency of 5 on x axis!)
Using Pandas plot function you can do:
import numpy as np
import pandas as pd
df = pd.DataFrame(np.random.randint(1,10,(90,1)),columns=['Values'])
df.plot(kind='bar', xticks=np.arange(0,90,5))
Or better:
df.plot(kind='bar', xticks=list(df.index[0::5]))
I 'm using Seaborn in a Jupyter notebook to plot histograms like this:
import numpy as np
import pandas as pd
from pandas import DataFrame
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
df = pd.read_csv('CTG.csv', sep=',')
sns.distplot(df['LBE'])
I have an array of columns with values that I want to plot histogram for and I tried plotting a histogram for each of them:
continous = ['b', 'e', 'LBE', 'LB', 'AC']
for column in continous:
sns.distplot(df[column])
And I get this result - only one plot with (presumably) all histograms:
My desired result is multiple histograms that looks like this (one for each variable):
How can I do this?
Insert plt.figure() before each call to sns.distplot() .
Here's an example with plt.figure():
Here's an example without plt.figure():
Complete code:
# imports
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = [6, 2]
%matplotlib inline
# sample time series data
np.random.seed(123)
df = pd.DataFrame(np.random.randint(-10,12,size=(300, 4)), columns=list('ABCD'))
datelist = pd.date_range(pd.datetime(2014, 7, 1).strftime('%Y-%m-%d'), periods=300).tolist()
df['dates'] = datelist
df = df.set_index(['dates'])
df.index = pd.to_datetime(df.index)
df.iloc[0]=0
df=df.cumsum()
# create distplots
for column in df.columns:
plt.figure() # <==================== here!
sns.distplot(df[column])
Distplot has since been deprecated in seaborn versions >= 0.14.0. You can, however, use sns.histplot() to plot histogram distributions of the entire dataframe (numerical features only) in the following way:
fig, axes = plt.subplots(2,5, figsize=(15, 5))
ax = axes.flatten()
for i, col in enumerate(df.columns):
sns.histplot(df[col], ax=ax[i]) # histogram call
ax[i].set_title(col)
# remove scientific notation for both axes
ax[i].ticklabel_format(style='plain', axis='both')
fig.tight_layout(w_pad=6, h_pad=4) # change padding
plt.show()
If, you specifically want a way to estimate the probability density function of a continuous random variable using the Kernel Density Function (mimicing the default behavior of sns.distplot()), then inside the sns.histplot() function call, add kde=True, and you will have curves overlaying the histograms.
Also works when looping with plt.show() inside:
for column in df.columns:
sns.distplot(df[column])
plt.show()
I am very new to pandas, and I have searched many StackOverflow questions similar to this for changing xtick labels yearly, but they all are different did not solve my problem, so I decided to ask my own question.
Here is my question. I have a mock data frame which I want to plot yearly xticks in the x-axis.
import numpy as np
import pandas as pd
df = pd.DataFrame({'date': pd.date_range('1991-01-01','2019-01-01')}).set_index('date')
df['value'] = np.random.randn(len(df))
df.plot()
This gives:
Xticks ==> 1995 2000 2005 etc
But I want ==> 1991 1992 ... 2019
How to do that?
So far I have tried this:
import matplotlib
import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline
fig,ax = plt.subplots()
df.plot(ax=ax)
ax.xaxis.set_major_locator(matplotlib.dates.YearLocator(base=1))
# ax.xaxis.set_minor_locator(matplotlib.dates.YearLocator(base=1))
# ax.set_xticklabels(list(df.index.time))
This gives just 2005 as xtick and nothing has worked till now.
Links I looked:
- Changing xticks in a pandas plot
- Python: Change the time on xticks for Pandas Plot
- https://matplotlib.org/3.1.1/api/dates_api.html
You need to use the x_compat=True argument to have pandas choose the units in a way that they are compatible with matplotlib.dates locators and formatters.
df.plot(ax=ax, x_compat=True)
Complete code:
import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
df = pd.DataFrame({'date': pd.date_range('1991-01-01','2019-01-01')}).set_index('date')
df['value'] = np.random.randn(len(df))
fig,ax = plt.subplots()
df.plot(ax=ax, x_compat=True)
ax.xaxis.set_major_locator(matplotlib.dates.YearLocator(base=1))
ax.xaxis.set_major_formatter(matplotlib.dates.DateFormatter("%Y"))
plt.show()
You can try this:
import datetime
# create xticks
xticks = pd.date_range(datetime.datetime(1990,1,1), datetime.datetime(2020,1,1), freq='YS')
# plot
fig, ax = plt.subplots(figsize=(12,8))
df['value'].plot(ax=ax,xticks=xticks.to_pydatetime())
ax.set_xticklabels([x.strftime('%Y') for x in xticks]);
plt.xticks(rotation=90);
Complete Example
import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import datetime
# data
df = pd.DataFrame({'date': pd.date_range('1991-01-01','2019-01-01')}).set_index('date')
df['value'] = np.random.randn(len(df))
# create xticks
xticks = pd.date_range(datetime.datetime(1990,1,1), datetime.datetime(2020,1,1), freq='YS')
# plot
fig, ax = plt.subplots(figsize=(12,8))
df['value'].plot(ax=ax,xticks=xticks.to_pydatetime())
ax.set_xticklabels([x.strftime('%Y') for x in xticks]);
plt.xticks(rotation=90);
plt.show()
This gives: