Pandas and Matplotlib
|
import pandas as pd
|
pd.series([values])
ad = {} area = pd.series(ad) |
|
Retrieving Values
|
area["a"]
To see all keys: area.keys() data.items() |
|
Dataframe as dictionary
|
area = pd.series({...})
data = pd.Dataframe({"area":area,}) |
|
Opening data
|
import pandas as pd
import numpy as np dat = np.genfromtxt('phoneBook.csv',delimiter =',',skip_header=1,dtype='<U16') |
|
Grouping
|
index = pd.MultiIndex.from_tuples(index)
index pop = pop.reindex(index) pop pop[:, 2010] |
|
Merging
|
pd.merge()
|
|
df = pd.merge()
|
|
|
Many to one
|
Duplicate entries
display('df3', 'df4', 'pd.merge(df3, df4)') |
|
Merge Key
|
Add on = "key column name"
|
|
Drop
|
.drop('name', axis=1)
|
|
Aggregation Functions
|
count() | Total number of items
first(), last() | First and last item mean(), median() | Mean and median min(), max() | Minimum and maximum std(), var() | Standard deviation and variance mad() | Mean absolute deviation prod() | Product of all items sum() | Sum of all items |
|
Grouping
|
name.groupy("key")
|
|
Pivot Tables by Hand
|
Require groupby
|
|
Pivot
|
name.pivot_table("what is taking the action", index = "groupby row" , columns = "groupbycol")
|
|
Aggregation Functions
|
name.pivot_table( index = "groupby row" , columns = "groupbycol" , aggfunc={'taking action':sum, 'taking action':'mean'})
|
|
Line Plots
|
Set linspace
x = np.linspace(0, 10, 100) |
|
Creating figure and axis
|
fig = plt.figure()
ax = plt.axes() |
|
Add graph and x,y
|
x = np.linspace(0, 10, 1000)
y = np.sin(x) plt.plot(x,y) plt.show() |
|
Changing linestyle and color
|
plt.plot(x,y,linestyle='--', color='c')
|
|
Multile curves and a legend
|
plt.plot(x,np.sin(x-.5),color='g',label="sin(x-0.5)")
plt.plot(x,np.sin(x-1),color='pink', label = "sin(x-1)") plt.plot(x,np.cos(x-0.5),color='c',linestyle='--',label = "cos(x-0.5)") plt.legend() plt.show() |
|
Adding limits
|
plt.xlim(-5,12)
plt.ylim(-2,2) |
|
Scatter Plot
|
x = np.random.randint(-1000,1000,150)
y = np.random.randint(-1000,1000,150) plt.scatter(x,y) or plt.plot(x,y,'o'); |
|
Other ways for plt
|
plt.xlabel() → ax.set_xlabel()
plt.ylabel() → ax.set_ylabel() lt.xlim() → ax.set_xlim() plt.ylim() → ax.set_ylim() plt.title() → ax.set_title() |
|
Histograms
|
fig = plt.figure()
ax = plt.axes() ax.hist(data); |
No comments yet.
Cheatography n. The art of mapping complex subjects into clear, instantly navigable reference guides.
