3

I am having data in a dataframe for each task with start time, end time and status. I want to draw a gantt chart for this. I tried following other question on stackoverflow (link) but they used numerical values so not able to use them. Below is the code.

import pandas as pd   
import matplotlib.pyplot as plt 
data = [['A', '2019-06-27 18:33:58.033', '2019-06-27 19:54:04.658', 'Success'], ['B', '2019-06-27 19:54:04.957', '2019-06-27 19:54:14.570', 'Success'], ['B', '2019-06-27 19:54:04.963', '2019-06-27 19:54:19.928', 'Failed']]
#Converting List to a dataframe
df = pd.DataFrame(data, columns = ['Task', 'Start Time', 'End Time', 'Status']) 
#Calculating the Time Difference
df['Duration'] = pd.to_datetime(df['End Time']) - pd.to_datetime(df['Start Time'])

color = {"Success":"turquoise", "Failed":"crimson"}
fig,ax=plt.subplots(figsize=(6,3))
labels=[]

for i, task in enumerate(df.groupby("Task")):
    labels.append(task[0])
    for r in task[1].groupby("Status"):
        data = r[1][["Start Time", "Duration"]]
        ax.broken_barh(data.values, (i-0.4,0.8), color=color[r[0]] )

ax.set_yticks(range(len(labels)))
ax.set_yticklabels(labels) 
ax.set_xlabel("time [ms]")
plt.tight_layout()       
plt.show()

Its not showing correct graph, may be due to time format. The above code works well if I use decimal numbers in place of time. Any help here.

LOrD_ARaGOrN
  • 3,884
  • 3
  • 27
  • 49
  • Have a look at this https://stackoverflow.com/questions/11042290/how-can-i-use-xaxis-date-with-barh, broken_barh expect numbers hence you can do the same to change your datetime – hashmuke Jun 28 '19 at 14:30

2 Answers2

3

I am able to draw the graph using time in matplotlib, however not able to color bars differently for success and failure. Solution with this feature is welcomed.

import pandas as pd    
from datetime import datetime
import matplotlib.dates as dates
import matplotlib.pyplot as plt
data = [['A', '2019-06-27 18:33:58.033', '2019-06-27 19:54:04.658', 'Success'], ['B', '2019-06-27 19:54:04.957', '2019-06-27 19:58:14.570', 'Success'], ['C', '2019-06-27 19:54:04.963', '2019-06-27 19:54:19.928', 'Failed']]
df = pd.DataFrame(data, columns = ['Task', 'Start_Time', 'End_Time', 'Status']) 

df_phase = df
df_phase['Start_Time'] = pd.to_datetime(df_phase['Start_Time'], format='%Y-%m-%d %H:%M:%S.%f')
df_phase['End_Time'] = pd.to_datetime(df_phase['End_Time'], format='%Y-%m-%d %H:%M:%S.%f')

#Convert DF columns into lists
sdate = df_phase['Start_Time'].tolist()
edate = df_phase['End_Time'].tolist()
tasks = df_phase['Task'].tolist()

#Convert time to Matplotlib number format
edate, sdate = [dates.date2num(item) for item in (edate, sdate)]
time_diff = edate - sdate
ypos = range(len(tasks))
fig, ax = plt.subplots()
ax.barh(ypos, time_diff, left=sdate, height=0.8, align='center', color='blue',edgecolor='black')
plt.yticks(ypos, tasks)
ax.axis('tight')

# We need to tell matplotlib that these are dates...
ax.xaxis_date()
plt.show()

Output Image:

enter image description here

LOrD_ARaGOrN
  • 3,884
  • 3
  • 27
  • 49
0

seems late though here is your code with slightly merged with Rishi's -

import pandas as pd   
import matplotlib.pyplot as plt 
data = [['A', '2019-06-27 18:33:58.033', '2019-06-27 19:54:04.658', 'Success'], ['B', '2019-06-27 19:54:04.957', '2019-06-27 19:54:14.570', 'Success'], ['C', '2019-06-27 19:54:04.963', '2019-06-27 20:54:19.928', 'Failed']]
#Converting List to a dataframe
df = pd.DataFrame(data, columns = ['Task', 'Start_Time', 'End_Time', 'Status']) 
#Calculating the Time Difference
#df['Duration'] = pd.to_datetime(df['End Time']) - pd.to_datetime(df['Start Time'])
df_phase = df
df_phase['Start_Time'] = pd.to_datetime(df_phase['Start_Time'], format='%Y-%m-%d %H:%M:%S')
df_phase['End_Time'] = pd.to_datetime(df_phase['End_Time'], format='%Y-%m-%d %H:%M:%S')

color = {"Success":"turquoise", "Failed":"crimson"}
#Convert DF columns into lists
sdate = df_phase['Start_Time'].tolist()
edate = df_phase['End_Time'].tolist()
tasks = df_phase['Task'].tolist()
#Convert time to Matplotlib number format
edate, sdate = [dates.date2num(item) for item in (edate, sdate)]
df_phase['Duration']=edate - sdate
fig,ax=plt.subplots(figsize=(6,3))
labels=[]

for i, task in enumerate(df_phase.groupby("Task")):
    labels.append(task[0])
    for r in task[1].groupby("Status"):
        data = r[1][["Start_Time", "Duration"]]
        ax.broken_barh(data.values, (i-0.4,0.8), color=color[r[0]] )

ax.set_yticks(range(len(labels)))
ax.set_yticklabels(labels) 
ax.set_xlabel("time [ms]")
plt.tight_layout()       
plt.show()

Output

Rahul Trivedi
  • 124
  • 1
  • 9