【449】backup get weekly tweets

import pandas as pd
from datetime import datetime

fn = r"D:\OneDrive - UNSW\tweets_flu.csv"
df = pd.read_csv(fn)
for i in range(len(df)):
	t = df.iloc[i]['created_at']
	w = datetime.strptime(t, "%Y-%m-%d %H:%M:%S").strftime("%W")
	ws.append(w)

ws = []
df['ws'] = ws
df['ws'].value_counts()

　

import pandas as pd
from datetime import datetime

fn = r"D:\OneDrive - UNSW\tweets_flu.csv"
df = pd.read_csv(fn)
for i in range(len(df)):
	t = df.iloc[i]['created_at']
	w = datetime.strptime(t, "%Y-%m-%d %H:%M:%S").strftime("%W")
	ws.append(w)

ws = []
df['ws'] = ws
df['ws'].value_counts()

wss = []

for i in a.index:
	wss.append((i, a[i]))

sorted(wss, key=lambda x:x[0])
[('12', 56), ('13', 22), ('14', 41), ('15', 52), ('16', 25), ('17', 45), ('18', 63), ('19', 54), ('20', 51), ('21', 143), ('22', 77), ('23', 53), ('24', 133), ('25', 93), ('26', 77), ('27', 125), ('28', 63), ('29', 67), ('30', 56), ('31', 67), ('32', 62), ('33', 67), ('34', 54), ('35', 41), ('36', 43), ('37', 24), ('38', 29), ('39', 33), ('40', 14)]

save data in csv file.

fn = r"D:\OneDrive - UNSW\01-UNSW\02-Papers\20190514-Prediction Location of Twitter\Data\Paper\weekly_tweets.csv"

fo = open(fn, "w+")
for e in a:
	fo.write(e[0] + ", " + str(e[1]) + "\n")

>>> import re
>>> def word_extraction(sentence):
	ignore = ['a', "the", "is"]
	words = re.sub("[^\w]", " ",  sentence).split()
	cleaned_text = [w.lower() for w in words if w not in ignore]
	return cleaned_text

>>> a = "alex is. good guy."
>>> word_extraction(a)
['alex', 'good', 'guy']
>>> a = ["fluence", 'good']
>>> b = 'flu'
>>> b in a
False
>>> 'go' in a
False
>>> 'good' in a
True

>>> import nltk
>>> nltk.download('stopwords')
[nltk_data] Downloading package stopwords to
[nltk_data]     C:\Users\z5194293\AppData\Roaming\nltk_data...
[nltk_data]   Unzipping corpora\stopwords.zip.
True
>>> from nltk.corpus import stopwords
>>> stopwords.words('english')
['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', 'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', 'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very', 's', 't', 'can', 'will', 'just', 'don', "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', 've', 'y', 'ain', 'aren', "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn', "hadn't", 'hasn', "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn', "mustn't", 'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't", 'won', "won't", 'wouldn', "wouldn't"]

Python 3.7.0 (v3.7.0:1bf9cc5093, Jun 27 2018, 04:59:51) [MSC v.1914 64 bit (AMD64)] on win32
Type "copyright", "credits" or "license()" for more information.
>>> fn = r"D:\Data\CSV\AUS_AVG_tweets_Centroid_Lon_lat.csv"
>>> import pandas as pd
>>> df = pd.read_csv(fn)
>>> df.head()
   OBJECTID_1  OBJECTID    ...           d_y   distance
0           1         1    ...      0.009560   1.149847
1           2         2    ...      0.204213  36.363808
2           3         3    ...     -0.003238   0.394919
3           4         4    ...      0.000109   1.063002
4           5         5    ...     -0.004560   0.549273

[5 rows x 14 columns]
>>> df.columns
Index(['OBJECTID_1', 'OBJECTID', 'SA2_NAME16', 'CENTROID_X', 'CENTROID_Y',
       'State', 'Count_', 'Avg_co_lon', 'Avg_co_lat', 'Shape_Length',
       'Shape_Area', 'd_x', 'd_y', 'distance'],
      dtype='object')
>>> dff = df[['SA2_NAME16']]
>>> dff.head()
                      SA2_NAME16
0                         Albany
1                  Albany Region
2  Alexander Heights - Koondoola
3             Alkimos - Eglinton
4           Applecross - Ardross
>>> dff = df[['SA2_NAME16', 'CENTROID_X']]
>>> dff.head()
                      SA2_NAME16  CENTROID_X
0                         Albany  117.899601
1                  Albany Region  118.207172
2  Alexander Heights - Koondoola  115.865812
3             Alkimos - Eglinton  115.677976
4           Applecross - Ardross  115.836085
>>> dff = df[['SA2_NAME16', 'CENTROID_X', 'CENTROID_Y', 'State', 'Avg_co_lon', 'Avg_co_lat', 'Shape_Area']]
>>> dff.head()
                      SA2_NAME16  CENTROID_X    ...      Avg_co_lat Shape_Area
0                         Albany  117.899601    ...      -35.017921   0.003012
1                  Albany Region  118.207172    ...      -34.923186   0.394533
2  Alexander Heights - Koondoola  115.865812    ...      -31.831628   0.000638
3             Alkimos - Eglinton  115.677976    ...      -31.600350   0.003104
4           Applecross - Ardross  115.836085    ...      -32.014606   0.000518

[5 rows x 7 columns]
>>> dff.columns
Index(['SA2_NAME16', 'CENTROID_X', 'CENTROID_Y', 'State', 'Avg_co_lon',
       'Avg_co_lat', 'Shape_Area'],
      dtype='object')
>>> dff.to_csv(r"D:\Data\CSV\AUS_AVG_tweets_Centroid_Lon_lat_lite.csv", index=False")

SyntaxError: EOL while scanning string literal
>>> dff.to_csv(r"D:\Data\CSV\AUS_AVG_tweets_Centroid_Lon_lat_lite.csv", index=False)

>>> dff = pd.read_csv(r"D:\Data\CSV\AUS_AVG_tweets_Centroid_Lon_lat_lite.csv")

>>> dff.head()

                            NAME       CEN_X    ...         AVG_Y      AREA
0                         Albany  117.899601    ...    -35.017921  0.003012
1                  Albany Region  118.207172    ...    -34.923186  0.394533
2  Alexander Heights - Koondoola  115.865812    ...    -31.831628  0.000638
3             Alkimos - Eglinton  115.677976    ...    -31.600350  0.003104
4           Applecross - Ardross  115.836085    ...    -32.014606  0.000518

[5 rows x 7 columns]
>>> dff.columns

Index(['NAME', 'CEN_X', 'CEN_Y', 'STATE', 'AVG_X', 'AVG_Y', 'AREA'], dtype='object')
>>>