Given the following data frame:
import numpy as np
import pandas as pd
df = pd.DataFrame({'Site':['a','a','a','b','b','b'],
'x':[1,1,0,1,np.nan,0],
'y':[1,np.nan,0,1,1,0]
})
df
Site y x
0 a 1.0 1
1 a NaN 1
2 a 0.0 0
3 b 1.0 1
4 b 1.0 NaN
5 b 0.0 0
I'd like to pivot this data frame to get the count of values (excluding "NaN") for each column.
I tried what I found in other posts, but nothing seems to work (maybe there was a change in pandas 0.18)?
Desired result:
Item count
Site
a y 2
b y 3
a x 3
b x 2
Thanks in advance!
pvt = pd.pivot_table(df, index = "Site", values = ["x", "y"], aggfunc = "count").stack().reset_index(level = 1)
pvt.columns = ["Item", "count"]
pvt
Out[38]:
Item count
Site
a x 3
a y 2
b x 2
b y 3
You can add pvt.sort_values("Item", ascending = False) if you want y's to appear first.
Related
I have a dataframe which I want to plot with matplotlib, but the index column is the time and I cannot plot it.
This is the dataframe (df3):
but when I try the following:
plt.plot(df3['magnetic_mag mean'], df3['YYYY-MO-DD HH-MI-SS_SSS'], label='FDI')
I'm getting an error obviously:
KeyError: 'YYYY-MO-DD HH-MI-SS_SSS'
So what I want to do is to add a new extra column to my dataframe (named 'Time) which is just a copy of the index column.
How can I do it?
This is the entire code:
#Importing the csv file into df
df = pd.read_csv('university2.csv', sep=";", skiprows=1)
#Changing datetime
df['YYYY-MO-DD HH-MI-SS_SSS'] = pd.to_datetime(df['YYYY-MO-DD HH-MI-SS_SSS'],
format='%Y-%m-%d %H:%M:%S:%f')
#Set index from column
df = df.set_index('YYYY-MO-DD HH-MI-SS_SSS')
#Add Magnetic Magnitude Column
df['magnetic_mag'] = np.sqrt(df['MAGNETIC FIELD X (μT)']**2 + df['MAGNETIC FIELD Y (μT)']**2 + df['MAGNETIC FIELD Z (μT)']**2)
#Subtract Earth's Average Magnetic Field from 'magnetic_mag'
df['magnetic_mag'] = df['magnetic_mag'] - 30
#Copy interesting values
df2 = df[[ 'ATMOSPHERIC PRESSURE (hPa)',
'TEMPERATURE (C)', 'magnetic_mag']].copy()
#Hourly Average and Standard Deviation for interesting values
df3 = df2.resample('H').agg(['mean','std'])
df3.columns = [' '.join(col) for col in df3.columns]
df3.reset_index()
plt.plot(df3['magnetic_mag mean'], df3['YYYY-MO-DD HH-MI-SS_SSS'], label='FDI')
Thank you !!
I think you need reset_index:
df3 = df3.reset_index()
Possible solution, but I think inplace is not good practice, check this and this:
df3.reset_index(inplace=True)
But if you need new column, use:
df3['new'] = df3.index
I think you can read_csv better:
df = pd.read_csv('university2.csv',
sep=";",
skiprows=1,
index_col='YYYY-MO-DD HH-MI-SS_SSS',
parse_dates='YYYY-MO-DD HH-MI-SS_SSS') #if doesnt work, use pd.to_datetime
And then omit:
#Changing datetime
df['YYYY-MO-DD HH-MI-SS_SSS'] = pd.to_datetime(df['YYYY-MO-DD HH-MI-SS_SSS'],
format='%Y-%m-%d %H:%M:%S:%f')
#Set index from column
df = df.set_index('YYYY-MO-DD HH-MI-SS_SSS')
EDIT: If MultiIndex or Index is from groupby operation, possible solutions are:
df = pd.DataFrame({'A':list('aaaabbbb'),
'B':list('ccddeeff'),
'C':range(8),
'D':range(4,12)})
print (df)
A B C D
0 a c 0 4
1 a c 1 5
2 a d 2 6
3 a d 3 7
4 b e 4 8
5 b e 5 9
6 b f 6 10
7 b f 7 11
df1 = df.groupby(['A','B']).sum()
print (df1)
C D
A B
a c 1 9
d 5 13
b e 9 17
f 13 21
Add parameter as_index=False:
df2 = df.groupby(['A','B'], as_index=False).sum()
print (df2)
A B C D
0 a c 1 9
1 a d 5 13
2 b e 9 17
3 b f 13 21
Or add reset_index:
df2 = df.groupby(['A','B']).sum().reset_index()
print (df2)
A B C D
0 a c 1 9
1 a d 5 13
2 b e 9 17
3 b f 13 21
You can directly access in the index and get it plotted, following is an example:
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
df = pd.DataFrame(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
#Get index in horizontal axis
plt.plot(df.index, df[0])
plt.show()
#Get index in vertiacal axis
plt.plot(df[0], df.index)
plt.show()
You can also use eval to achieve this:
In [2]: df = pd.DataFrame({'num': range(5), 'date': pd.date_range('2022-06-30', '2022-07-04')}, index=list('ABCDE'))
In [3]: df
Out[3]:
num date
A 0 2022-06-30
B 1 2022-07-01
C 2 2022-07-02
D 3 2022-07-03
E 4 2022-07-04
In [4]: df.eval('index_copy = index')
Out[4]:
num date index_copy
A 0 2022-06-30 A
B 1 2022-07-01 B
C 2 2022-07-02 C
D 3 2022-07-03 D
E 4 2022-07-04 E
I have a dataset with lots of variables. So I've extracted the numeric ones:
numeric_columns = transposed_df.select_dtypes(np.number)
Then I want to replace all 0 values for 0.0001
transposed_df[numeric_columns.columns] = numeric_columns.where(numeric_columns.eq(0, axis=0), 0.0001)
And here is the first problem. This line is not replacing the 0 values with 0.0001, but is replacing all non zero values with 0.0001.
Also after this (replacing the 0 values by 0.0001) I want to replace all values there are less than the 1th quartile of the row to -1 and leave the others as they were. But I am not managing how.
To answer your first question
In [36]: from pprint import pprint
In [37]: pprint( numeric_columns.where.__doc__)
('\n'
'Replace values where the condition is False.\n'
'\n'
'Parameters\n'
'----------\n'
because of that your all the values except 0 are getting replaced
Use DataFrame.mask and for second condition compare by DataFrame.quantile:
transposed_df = pd.DataFrame({
'A':list('abcdef'),
'B':[0,0.5,4,5,5,4],
'C':[7,8,9,4,2,3],
'D':[1,3,0,7,1,0],
'E':[5,3,6,9,2,4],
'F':list('aaabbb')
})
numeric_columns = transposed_df.select_dtypes(np.number)
m1 = numeric_columns.eq(0)
m2 = numeric_columns.lt(numeric_columns.quantile(q=0.25, axis=1), axis=0)
transposed_df[numeric_columns.columns] = numeric_columns.mask(m1, 0.0001).mask(m2, -1)
print (transposed_df)
A B C D E F
0 a -1.0 7 1.0 5 a
1 b -1.0 8 3.0 3 a
2 c 4.0 9 -1.0 6 a
3 d 5.0 -1 7.0 9 b
4 e 5.0 2 -1.0 2 b
5 f 4.0 3 -1.0 4 b
EDIT:
from scipy.stats import zscore
print (transposed_df[numeric_columns.columns].apply(zscore))
B C D E
0 -2.236068 0.570352 -0.408248 0.073521
1 0.447214 0.950586 0.408248 -0.808736
2 0.447214 1.330821 -0.816497 0.514650
3 0.447214 -0.570352 2.041241 1.838037
4 0.447214 -1.330821 -0.408248 -1.249865
5 0.447214 -0.950586 -0.816497 -0.367607
EDIT1:
transposed_df = pd.DataFrame({
'A':list('abcdef'),
'B':[0,1,1,1,1,1],
'C':[1,8,9,4,2,3],
'D':[1,3,0,7,1,0],
'E':[1,3,6,9,2,4],
'F':list('aaabbb')
})
numeric_columns = transposed_df.select_dtypes(np.number)
from scipy.stats import zscore
df1 = pd.DataFrame(numeric_columns.apply(zscore, axis=1).tolist(),index=transposed_df.index)
transposed_df[numeric_columns.columns] = df1
print (transposed_df)
A B C D E F
0 a -1.732051 0.577350 0.577350 0.577350 a
1 b -1.063410 1.643452 -0.290021 -0.290021 a
2 c -0.816497 1.360828 -1.088662 0.544331 a
3 d -1.402136 -0.412393 0.577350 1.237179 b
4 e -1.000000 1.000000 -1.000000 1.000000 b
5 f -0.632456 0.632456 -1.264911 1.264911 b
I need to delete the row completely in a dataframe having "None" value in all the columns. I am using the following code -
df.dropna(axis=0,how='all',thresh=None,subset=None,inplace=True)
This does not bring any difference to the dataframe. The rows with "None" value are still there.
How to achieve this?
There Nones should be strings, so use replace first:
df = df.replace('None', np.nan).dropna(how='all')
df = pd.DataFrame({
'a':['None','a', 'None'],
'b':['None','g', 'None'],
'c':['None','v', 'b'],
})
print (df)
a b c
0 None None None
1 a g v
2 None None b
df1 = df.replace('None', np.nan).dropna(how='all')
print (df1)
a b c
1 a g v
2 NaN NaN b
Or test values None with not equal and DataFrame.any:
df1 = df[df.ne('None').any(axis=1)]
print (df1)
a b c
1 a g v
2 None None b
You should be dropping in the axis 1. Use the how keyword to drop columns with any or all NaN values. Check the docs
import pandas as pd
import numpy as np
df = pd.DataFrame({'a':[1,2,3], 'b':[-1, 0, np.nan], 'c':[np.nan, np.nan, np.nan]})
df
a b c
0 1 -1.0 NaN
1 2 0.0 NaN
2 3 NaN 5.0
df.dropna(axis=1, how='any')
a
0 1
1 2
2 3
df.dropna(axis=1, how='all')
a b
0 1 -1.0
1 2 0.0
2 3 NaN
I have my data like this in pandas dataframe python
df = pd.DataFrame({
'ID':range(1, 8),
'Type':list('XXYYZZZ'),
'Value':[2,3,2,9,6,1,4]
})
The oputput that i want to generate is
How can i generate these results using python pandas dataframe. I want to include all the Y values of type column, and does not want to aggregate them.
First filter values by boolean indexing, aggregate and append filter out rows, last sorting:
mask = df['Type'] == 'Y'
df1 = (df[~mask].groupby('Type', as_index=False)
.agg({'ID':'first', 'Value':'sum'})
.append(df[mask])
.sort_values('ID'))
print (df1)
ID Type Value
0 1 X 5
2 3 Y 2
3 4 Y 9
1 5 Z 11
If want range 1 to length of data for ID column:
mask = df['Type'] == 'Y'
df1 = (df[~mask].groupby('Type', as_index=False)
.agg({'ID':'first', 'Value':'sum'})
.append(df[mask])
.sort_values('ID')
.assign(ID = lambda x: np.arange(1, len(x) + 1)))
print (df1)
ID Type Value
0 1 X 5
2 2 Y 2
3 3 Y 9
1 4 Z 11
Another idea is create helper column for unique values only for Y rows and aggregate by both columns:
mask = df['Type'] == 'Y'
df['g'] = np.where(mask, mask.cumsum() + 1, 0)
df1 = (df.groupby(['Type','g'], as_index=False)
.agg({'ID':'first', 'Value':'sum'})
.drop('g', axis=1)[['ID','Type','Value']])
print (df1)
ID Type Value
0 1 X 5
1 3 Y 2
2 4 Y 9
3 5 Z 11
Similar alternative with Series g, then drop is not necessary:
mask = df['Type'] == 'Y'
g = np.where(mask, mask.cumsum() + 1, 0)
df1 = (df.groupby(['Type',g], as_index=False)
.agg({'ID':'first', 'Value':'sum'})[['ID','Type','Value']])
I am trying to calculate additional metrics from existing pandas dataframe by using an if/else condition on existing column values.
if(df['Sell_Ind']=='N').any():
df['MarketValue'] = df.apply(lambda row: row.SharesUnits * row.CurrentPrice, axis=1).astype(float).round(2)
elif(df['Sell_Ind']=='Y').any():
df['MarketValue'] = df.apply(lambda row: row.SharesUnits * row.Sold_price, axis=1).astype(float).round(2)
else:
df['MarketValue'] = df.apply(lambda row: 0)
For the if condition the MarketValue is calculated correctly but for the elif condition, its not giving the correct value.
Can anyone point me as what wrong I am doing in this code.
I think you need numpy.select, apply can be removed and multiple columns by mul:
m1 = df['Sell_Ind']=='N'
m2 = df['Sell_Ind']=='Y'
a = df.SharesUnits.mul(df.CurrentPrice).astype(float).round(2)
b = df.SharesUnits.mul(df.Sold_price).astype(float).round(2)
df['MarketValue'] = np.select([m1, m2], [a,b], default=0)
Sample:
df = pd.DataFrame({'Sold_price':[7,8,9,4,2,3],
'SharesUnits':[1,3,5,7,1,0],
'CurrentPrice':[5,3,6,9,2,4],
'Sell_Ind':list('NNYYTT')})
#print (df)
m1 = df['Sell_Ind']=='N'
m2 = df['Sell_Ind']=='Y'
a = df.SharesUnits.mul(df.CurrentPrice).astype(float).round(2)
b = df.SharesUnits.mul(df.Sold_price).astype(float).round(2)
df['MarketValue'] = np.select([m1, m2], [a,b], default=0)
print (df)
CurrentPrice Sell_Ind SharesUnits Sold_price MarketValue
0 5 N 1 7 5.0
1 3 N 3 8 9.0
2 6 Y 5 9 45.0
3 9 Y 7 4 28.0
4 2 T 1 2 0.0
5 4 T 0 3 0.0