https://pbpython.com/simple-graphing-pandas.html
"""
Getting Started
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
pd.__version__
'0.23.4'
%matplotlib inline
sales=pd.read_csv("https://pbpython.com/extras/sample-salesv2.csv")
sales.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 8 columns):
account number 1000 non-null int64
name 1000 non-null object
sku 1000 non-null object
category 1000 non-null object
quantity 1000 non-null int64
unit price 1000 non-null float64
ext price 1000 non-null float64
date 1000 non-null object
dtypes: float64(2), int64(2), object(4)
memory usage: 62.6+ KB
sales=pd.read_csv("https://pbpython.com/extras/sample-salesv2.csv", parse_dates=['date'])
import pandas as pd
import numpy as np
df = pd.read_excel("../data/sample-salesv3.xlsx")
df['date'] = pd.to_datetime(df['date'])
df.head()
import pandas as pd
import numpy as np
df = pd.read_excel("../data/sample-salesv3.xlsx")
df['date'] = pd.to_datetime(df['date'])
df = df.sort_values(by=['date'])
df[df['date'] >='20140905'].head()
df[df['date'] >='2014-03'].head()
df[(df['date'] >='20140701') & (df['date'] <= '20140715')].head()
df[df['date'] >= 'Oct-2014'].head()
df[df['date'] >= '10-10-2014'].head()
df2 = df.set_index(['date'])
df2["20140101":"20140201"].head()
df2["2014-Jan-1":"2014-Feb-1"].head()
df2["2014"].head()
df2["2014-Dec"].head()
import xlwings as xw
import numpy as np
import pandas as pd
import datetime as dt
import time
import sys
# Fire up a new book in the active Excel instance
wb1 = xw.Book()
# Connects to an unsaved book (looks in all Excel instances)
wb1 = xw.Book('Book1')
sheet = wb1.sheets[0]
# Create Datetime from string/text
sheet.range('A1').value = dt.datetime(2014, 12, 9, 12, 3, 25)
sheet.range('A1').value
import pandas as pd
df = pd.read_excel("https://github.com/chris1610/pbpython/blob/master/data/sample-salesv3.xlsx?raw=True")
df["date"] = pd.to_datetime(df['date'])
df.head()
df.info()
# grouping time series and resample by month:
df.set_index('date').resample('M')["ext price"].sum()
df.set_index('date').groupby('name')["ext price"].resample("M").sum()
df.groupby(['name', pd.Grouper(key='date', freq='M')])['ext price'].sum()
# grouping time series and resample by the end of month:
df.groupby(['name', pd.Grouper(key='date', freq='A-DEC')])['ext price'].sum()
"""
B-006 - Simple Graphing with IPython and Pandas
https://pbpython.com/simple-graphing-pandas.html
"""
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
sales=pd.read_csv("https://pbpython.com/extras/sample-salesv2.csv", parse_dates=['date'])
purchase_patterns = sales[['ext price','date']]
purchase_patterns = purchase_patterns.set_index('date')
purchase_plot = purchase_patterns.resample('M').sum().plot(title="Total Sales by Month",legend=None)
fig = purchase_plot.get_figure()
# fig.savefig("total-sales.png")