CoCalc -- Untitled.ipynb

¹³⁹ views

Kernel: Python 3 (Ubuntu Linux)

In [3]:

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib as mpl
from datetime import datetime

In [0]:

In [4]:

import os
os.listdir()

Out[4]:

['.bash_profile',
 '.jupyter-blobs-v0.db',
 'raw.csv',
 '.Untitled.ipynb.sage-jupyter2',
 '.sage',
 '.config',
 '.cache',
 'Untitled.ipynb',
 '.smc',
 '.ssh',
 '.local',
 '.bashrc',
 '.ipython',
 '.snapshots']

In [5]:

df = pd.read_csv('raw.csv')

In [6]:

df.head()

Out[6]:

In [7]:

df.tail()

Out[7]:

In [8]:

df.describe(include=['O'])

Out[8]:

In [9]:

df.info()
df[' Serial']

Out[9]:

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 37123 entries, 0 to 37122
Data columns (total 3 columns):
Date         37123 non-null object
 Serial      37123 non-null object
 RawValue    37123 non-null int64
dtypes: int64(1), object(2)
memory usage: 870.1+ KB

       28-000006794411
       28-000006794411
       28-000006794411
       28-000006794411
       28-000006794411
       28-000006794411
       28-000006794411
       28-000006794411
       28-000006794411
       28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
      28-000006794411
               ...       
   28-00000220db9f
   28-00000220db9f
   28-000008ab5383
   28-000008ab5383
   28-000008ab5383
   28-000008ab5383
   10-000802b68231
   10-000802b68231
   10-000802b68231
   10-000802b68231
   28-00000220db9f
   28-00000220db9f
   28-00000220db9f
   28-00000220db9f
   28-000008ab5383
   28-000008ab5383
   28-000008ab5383
   28-000008ab5383
   10-000802b68231
   10-000802b68231
   10-000802b68231
   10-000802b68231
   28-00000220db9f
   28-00000220db9f
   28-00000220db9f
   28-00000220db9f
   28-000008ab5383
   28-000008ab5383
   28-000008ab5383
   28-000008ab5383
Name:  Serial, Length: 37123, dtype: object

In [10]:

temp = df[['Date',' Serial',' RawValue']].groupby([' Serial'],as_index=False).mean()

In [11]:

temp.loc[0,' Serial']

Out[11]:

' 10-000802b68231'

In [12]:

temp[' Serial']

Out[12]:

   10-000802b68231
   28-00000220db9f
   28-000006794411
   28-000008ab5383
Name:  Serial, dtype: object

In [13]:

dfall = [pd.DataFrame({
    'Date': df.loc[df[' Serial']==temp.loc[0,' Serial'],'Date'].copy(),
    'RawValue': df.loc[df[' Serial']==temp.loc[0,' Serial'],' RawValue'].copy(),
})]
dfall[0].reset_index(inplace=True)
dfall[0]['DateTime'] = pd.to_datetime(dfall[0].Date,format='%Y-%m-%dT%H:%M:%S.%f')
for i in range(0,3):
    dfall.append(pd.DataFrame({
    'Date': df.loc[df[' Serial']==temp.loc[i+1,' Serial'],'Date'].copy(),
    'RawValue': df.loc[df[' Serial']==temp.loc[i+1,' Serial'],' RawValue'].copy(),
    }))
    dfall[i+1].reset_index(inplace=True)
    dfall[i+1]['DateTime'] = pd.to_datetime(dfall[i+1].Date,format='%Y-%m-%dT%H:%M:%S.%f')

In [22]:

dfall[0].head()

Out[22]:

In [0]:

In [0]:

In [0]:

In [24]:

plt.figure(figsize=(10,7))
i = 0
dbegin = datetime(2017,2,6,18)
dbegin = datetime(2017,2,7,3)
dend = datetime(2019,2,7,12)
clipdata = (dfall[i].RawValue > 22000) & (dfall[i].DateTime < dend)
clipdata = (dfall[i].DateTime < dend) & (dfall[i].DateTime > dbegin)
tempdf = dfall[i][clipdata]
tempdf.reset_index(inplace=True)
x = tempdf.DateTime
y = tempdf.RawValue/1000
dtstart = x[0]
plt.plot(x,y)
plt.show()

Out[24]:

In [15]:

plt.figure(figsize=(10,7))
i = 0
dbegin = datetime(2018,2,6,18)
dbegin = datetime(2018,2,7,3)
dend = datetime(2018,2,7,12)
clipdata = (dfall[i].RawValue > 22000) & (dfall[i].DateTime < dend)
clipdata = (dfall[i].DateTime < dend) & (dfall[i].DateTime > dbegin)
tempdf = dfall[i][clipdata]
tempdf.reset_index(inplace=True)
x = tempdf.DateTime
y = tempdf.RawValue/1000
dtstart = x[0]
plt.plot(x,y)
plt.show()

Out[15]:

In [16]:

plt.figure(figsize=(10,7))
i = 1
clipdata = (dfall[i].DateTime < dend) & (dfall[i].DateTime > dbegin)
x1 = dfall[i][clipdata].DateTime
y1 = dfall[i][clipdata].RawValue/1000
plt.plot(x1,y1)
plt.show()

Out[16]:

In [17]:

plt.figure(figsize=(10,7))
i = 3
clipdata = (dfall[i].DateTime < dend) & (dfall[i].DateTime > dbegin)
x3 = dfall[i][clipdata].DateTime
y3 = dfall[i][clipdata].RawValue/1000
plt.plot(x3,y3)
plt.show()

Out[17]:

In [18]:

plt.figure(figsize=(20,12))
plt.plot(x,y,x1,y1,x3,y3)
plt.show()

Out[18]:

In [19]:

dfall[1].DateTime[0]

Out[19]:

Timestamp('2018-02-05 21:24:15.926087')

In [20]:

dtstart

Out[20]:

Timestamp('2018-02-07 03:00:04.012627')

In [21]:

Out[21]:

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-21-e983f374794d> in <module>()
----> 1 d

NameError: name 'd' is not defined

In [0]:

In [0]:

Product

Resources

Company