In [ ]:
x = 10
In [ ]:
x = 'hello'
In [ ]:
x = 2.7
In [ ]:
y = 1.0
In [ ]:
z = x + y
print(z)
I want a list of numbers
In [ ]:
items = [2.7, 3.1, 69.1]
I want to print the second number in the list
In [ ]:
print(items[1])
I want to print the length of the list
In [ ]:
print len(items)
I want to print all the numbers in the list
In [ ]:
for item in items:
print item
In [ ]:
import pandas as pd
In [ ]:
df = pd.read_csv("sample.csv")
In [ ]:
df
In [ ]:
df.columns = ["area", "sales2014", "profit", "sales2016"]
In [ ]:
df.dtypes
How many rows & columns does the dataframe have?
In [ ]:
?df.shape
I want to see the top 5 rows of the dataframe
In [ ]:
df.shape
In [ ]:
df.head
In [ ]:
df1 = df.head(1)
In [ ]:
df1
I want to see the bottom 2 rows only
In [ ]:
df.tail(2)
In [ ]:
df.index
What are the column names?
In [ ]:
df.columns
Show me the values of the dataframe. (exclude the column and index information)
In [ ]:
df.values
Can I quickly get a sense of how the data is in the dataframe? Information like min, max, mean etc
In [ ]:
df.sales.describe()
I want to sort the dataframe based on sales in descending order
In [ ]:
df.sort_values(by=['sales2014', "profit"], ascending=False)
I want to do the same, but based on profit column
In [ ]:
df.sort_values(by='profit', ascending=False)
I want to find the area with least profit & sales
In [ ]:
df.sort_values(by=['sales','profit'], ascending=True)
I want to view the sales alone
In [ ]:
df.sales
I want to view just sales & profit columns, not the area names
In [ ]:
df.loc[2:4, ['sales2014', 'profit']]
I want the third row of the dataframe
In [ ]:
df.loc[2, :]
I want the third row, sales & profit columns
In [ ]:
df.loc[2, ['sales', 'profit']]
I want rows between index 2 and 3, and column 2 only
In [ ]:
df.iloc[2:3, 2]
In [ ]: