I am trying to set an ARIMA model to some data, for this, I used 'autocorrelation_plot()' with my time series. It's generates however the error in the title.
I have an attribute table composed, among others, of a Date and time fiels.
I extracted them (after transforming the attribute table into a numpy table), put them in a 'datetime' variable and appended them all in a list:
O,A = [],[]
dt = datetime.strptime(dt1, "%Y/%m/%d %H:%M")
A.append(dt)
I tried then to create time series and printed them to be sure of the results:
data2 = pd.Series(A, O)
print data2
The results were satisfying, until I decided to auto-correlate :
Auto-correlation command :
autocorrelation_plot(data2)
After this command, it returns:
TypeError: ufunc add cannot use operands with types dtype('M8[ns]') and dtype('M8[ns]')
I guess it's due to the conversion of the datetime.strptime to a numpy ?
I tried to follow some suggestions from previous questions
index.to_pydatetime() , dtype, M8[ns] error ..., in vain.
Minimal reproducible example:
from pandas import datetime
from pandas import DataFrame
import pandas as pd
from matplotlib import pyplot as plt
from pandas.tools.plotting import autocorrelation_plot
arr = arcpy.da.TableToNumPyArray(inTable ,("PROVINCE","ZONE_CODE","MEAN", "Datetime","Time"))
arr_length = len(arr)
j = 1
O,A = [],[]
while j<=55: #I have 55 provinces
i = 0
while i<arr_length:
if arr[i][1]== j:
O.append(arr[i][2])
c = str(arr[i][3])
d = str(c[0:4]+"/"+c[5:7]+"/"+c[8:10])
t = str(arr[i][4])
if t=="10":
dt1 = str(d+" 10:00")
else:
dt1 = str(d+" 14:00")
dt = datetime.strptime(dt1, "%Y/%m/%d %H:%M")
A.append(dt)
i = i+1
data2 = pd.Series(A, O)
print data2
autocorrelation_plot(data2)
del A[:]
del O[:]
j += 1
Screenshot of the results:
results
I used this to solve my issue:
import matplotlib.dates as mpl_dates
df.reset_index(inplace=True)
df['Date']=df['Date'].apply(mpl_dates.date2num)
df = df.astype(float)
I found a solution, it can look barbaric, but it works!
I've just "recreated" pd.Series() with the pd.Series I had:
data2 = pd.Series(O, A)
autocorrelation_plot(pd.Series(data2))
plt.show()
Related
PostGres SQL will not accept data which is in violation of primary key. To ignore the duplicate data, I have this code:
import pandas as pd
import psycopg2
import os
import matplotlib
from sqlalchemy import create_engine
from tqdm import tqdm_notebook
from pandas_datareader import data as web
import datetime
from dateutil.relativedelta import relativedelta
db_database = os.environ.get('123')
engine = create_engine('postgresql://postgres:{}#localhost:5433/stockdata'.format(123))
def import_data(Symbol):
df = web.DataReader(Symbol, 'yahoo',start=datetime.datetime.now()-relativedelta(days=3), end= datetime.datetime.now())
insert_init = """INSERT INTO stockprices
(Symbol, Date, Volume, Open, Close, High, Low)
VALUES
"""
vals = ",".join(["""('{}','{}','{}','{}','{}','{}','{}')""".format(
Symbol,
Date,
row.High,
row.Low,
row.Open,
row.Close,
row.Volume,
) for Date, row in df.iterrows()])
insert_end ="""ON CONFLICT (Symbol, Date) DO UPDATE
SET
Volume = EXCLUDED.Volume,
Open = EXCLUDED.Open,
Close = EXCLUDED.Close,
Low = EXCLUDED.Low,
High = EXCLUDED.High
"""
query = insert_init + vals + insert_end
engine.execute(query)
import_data('aapl')
I am getting this error:
ProgrammingError: (psycopg2.errors.UndefinedColumn) column "symbol" of relation "stockprices" does not exist
LINE 2: (Symbol,Date, Volume, Open, Close, H...
^
[SQL: INSERT INTO stockprices
Could you please advise as to what does this error mean? I got rid of all the double quotes as advised in the comment.
I had used this code to create the table:
def create_price_table(symbol):
print(symbol)
df = web.DataReader(symbol, 'yahoo', start=datetime.datetime.now()-relativedelta(days=7), end= datetime.datetime.now())
df['Symbol'] = symbol
df.to_sql(name = "stockprices", con = engine, if_exists='append', index = True)
return 'daily prices table created'
create_price_table('amzn')
Also as was mentioned in the comment. I used this to check the table name:
SELECT table_name
FROM information_schema.tables
WHERE table_schema='public'
AND table_type='BASE TABLE';
Edit 1:
I changed the code as suggested in the comment, now the column name is in small case. Below is the code:
import pandas as pd
import psycopg2
import os
import matplotlib
from sqlalchemy import create_engine
from tqdm import tqdm_notebook
from pandas_datareader import data as web
import datetime
from dateutil.relativedelta import relativedelta
db_database = os.environ.get('123')
engine = create_engine('postgresql://postgres:{}#localhost:5433/stockdata'.format(123))
def create_price_table(symbol):
print(symbol)
df = web.DataReader(symbol, 'yahoo', start=datetime.datetime.now()-relativedelta(days=7), end= datetime.datetime.now())
df['symbol'] = symbol
df = df.rename(columns= {'Open':'open'})
df = df.rename(columns= {'Close':'close'})
df = df.rename(columns= {'High':'high'})
df = df.rename(columns= {'Low':'low'})
df = df.rename(columns= {'Volume':'volume'})
df = df.rename(columns= {'Adj Close':'adj_close'})
df.index.name ='date'
df.to_sql(name = "stockprices", con = engine, if_exists='append', index = True)
return 'daily prices table created'
# create_price_table('amzn')
def import_data(Symbol):
df = web.DataReader(Symbol, 'yahoo', start=datetime.datetime.now()-relativedelta(days=3), end= datetime.datetime.now())
insert_init = """INSERT INTO stockprices
(symbol, date, volume, open, close, high, low)
VALUES
"""
vals = ",".join(["""('{}','{}','{}','{}','{}','{}','{}')""".format(
Symbol,
Date,
row.High,
row.Low,
row.Open,
row.Close,
row.Volume,
) for Date, row in df.iterrows()])
insert_end ="""ON CONFLICT (Symbol, Date) DO UPDATE
SET
Volume = EXCLUDED.Volume,
Open = EXCLUDED.Open,
Close = EXCLUDED.Close,
Low = EXCLUDED.Low,
High = EXCLUDED.High
"""
query = insert_init + vals + insert_end
engine.execute(query)
import_data('aapl')
This code however is producing a new error:
DataError: (psycopg2.errors.InvalidTextRepresentation) invalid input syntax for type bigint: "166.14999389648438"
LINE 4: ('aapl','2022-02-23 00:00:00','166.14999...
^
Per my comment you have two issues:
You are trying to INSERT a float value(166.14999389648438) into an integer field. First thing to figure out is why the mismatch? Do really want the database field to be an integer? Second thing is that trying to force a float into an integer will work if the value is being entered as a float/numeric:
select 166.14999389648438::bigint; 166
Though as you see it gets truncated.
It will not work if entered as a string:
ERROR: invalid input syntax for type bigint: "166.14999389648438"
Which is what you are doing. This leads to the second issue below.
You are not using proper Parameter passing as shown in the link. Where among other things is the warning:
Warning
Never, never, NEVER use Python string concatenation (+) or string parameters interpolation (%) to pass variables to a SQL query string. Not even at gunpoint.
For the purposes of this question the important part is that using parameter passing will result in proper type adaptation.
import pandas as pd
import numpy as np
from statsmodels.miscmodels.ordinal_model import OrderedModel
import warnings
warnings.simplefilter("ignore")
data = pd.read_csv("filtered aggregated data.csv")
mask = data["Fit"].str.contains("Storefront").astype(bool)
data = data[~mask]
data["6 Mo. Growth Count"] = data["6 Mo. Growth
Count"].fillna("NaN")
sixMoData = data[data["6 Mo. Growth Count"] != "NaN"]
sixMoData["Fit"] = sixMoData["Fit"].astype("category")
sixMoData = pd.get_dummies(sixMoData, columns=
["Category","Country"])
sixMoData.dropna(inplace=True)
sixMoData.reset_index(inplace=True)
X = sixMoData[sixMoData.columns[3:]]
y = sixMoData["Fit"]
for col in X.columns:
containsNa = any(X[col].isna())
containsInf = any(X[col].isin([np.inf, -np.inf]))
if containsNa or containsInf:
print(col)
X[col] = X[col].astype(float)
model = OrderedModel(y, X)
When I run this code, I find that there are no columns that contain an nan value based on the checks that I run here. However, when I try to run the model, I get an error stating: "exog contains inf or nans", where exog refers to the X dataframe. What am I doing incorrectly when checking for nans?
I Have a DF in which I am trying to convert the eastings/northings to long/lats. My df looks like this:
import pandas as pd
import numpy as np
import pyproj
Postcode Eastings Northings
0 AB101AB 394235 806529
1 AB101AF 394181 806429
2 AB101AG 394230 806469
3 AB101AH 394371 806359
4 AB101AL 394296 806581
I am using a well know code block to convert the eastings and northings to long/lats and add those long/lats as new columns to the df:
def proj_transform(df):
bng = pyproj.Proj("+init=EPSG:27700")
wgs84 = pyproj.Proj("+init=EPSG:4326")
lats = pd.Series()
lons = pd.Series()
for idx, val in enumerate(df['Eastings']):
lon, lat = pyproj.transform(bng, wgs84, df['Eastings'][idx], df['Northings'][idx])
lats.set_value(idx, lat)
lons.set_value(idx, lon)
df['lat'] = lats
df['lon'] = lons
return df
df_transform = proj_transform(my_df)
However, I keep getting the following error, "input must be an array, list, tuple or scalar". Does anyone have any insight into where I am going wrong here?
This is the fastest method:
https://gis.stackexchange.com/a/334307/144357
from pyproj import Transformer
trans = Transformer.from_crs(
"EPSG:27700",
"EPSG:4326",
always_xy=True,
)
xx, yy = trans.transform(my_df["Eastings"].values, my_df["Northings"].values)
my_df["X"] = xx
my_df["Y"] = yy
Also helpful for reference:
https://pyproj4.github.io/pyproj/stable/gotchas.html#upgrading-to-pyproj-2-from-pyproj-1
https://pyproj4.github.io/pyproj/stable/gotchas.html#init-auth-auth-code-should-be-replaced-with-auth-auth-code
https://pyproj4.github.io/pyproj/stable/gotchas.html#axis-order-changes-in-proj-6
You can use DataFrame.apply with axis=1 and change function like:
def proj_transform(x):
e = x['Eastings']
n = x['Northings']
bng = pyproj.Proj("+init=EPSG:27700")
wgs84 = pyproj.Proj("+init=EPSG:4326")
lon, lat = pyproj.transform(bng, wgs84, e, n)
return pd.Series([lon, lat])
my_df[['lat','lon']] = my_df.apply(proj_transform, axis=1)
Suppose that I have an array
a = np.array([[1,2.5,3,4],[1, 2.5, 3,3]])
I want to find the mode of each column without using stats.mode().
The only way I can think of is the following:
result = np.zeros(a.shape[1])
for i in range(len(result)):
curr_col = a[:,i]
result[i] = curr_col[np.argmax(np.unique(curr_col, return_counts = True))]
update:
There is some error in the above code and the correct one should be:
values, counts = np.unique(a[:,i], return_counts = True)
result[i] = values[np.argmax(counts)]
I have to use the loop because np.unique does not output compatible result for each column and there is no way to use np.bincount because the dtype is not int.
If you look at the numpy.unique documentation, this function returns the values and the associated counts (because you specified return_counts=True). A slight modification of your code is necessary to give the correct result. What you are trying todo is to find the value associated to the highest count:
import numpy as np
a = np.array([[1,5,3,4],[1,5,3,3],[1,5,3,3]])
result = np.zeros(a.shape[1])
for i in range(len(result)):
values, counts = np.unique(a[:,i], return_counts = True)
result[i] = values[np.argmax(counts)]
print(result)
Output:
% python3 script.py
[1. 5. 3. 4.]
Here is a code tha compares your solution with the scipy.stats.mode function:
import numpy as np
import scipy.stats as sps
import time
a = np.random.randint(1,100,(100,100))
t_start = time.time()
result = np.zeros(a.shape[1])
for i in range(len(result)):
values, counts = np.unique(a[:,i], return_counts = True)
result[i] = values[np.argmax(counts)]
print('Timer 1: ', (time.time()-t_start), 's')
t_start = time.time()
result_2 = sps.mode(a, axis=0).mode
print('Timer 2: ', (time.time()-t_start), 's')
print('Matrices are equal!' if np.allclose(result, result_2) else 'Matrices differ!')
Output:
% python3 script.py
Timer 1: 0.002721071243286133 s
Timer 2: 0.003339052200317383 s
Matrices are equal!
I tried several values for parameters and your code is actually faster than scipy.stats.mode function so it is probably close to optimal.
I am trying to implement a time fold function to be 'map'ed to various partitions of a dask dataframe which in turn changes the shape of the dataframe in question (or alternatively produces a new dataframe with the altered shape). This is how far I have gotten. The result 'res' returned on compute is a list of 3 delayed objects. When I try to compute each of them in a loop (last tow lines of code) this results in a "TypeError: 'DataFrame' object is not callable" After going through the examples for map_partitions, I also tried altering the input DF (inplace) in the function with no return value which causes a similar TypeError with NoneType. What am I missing?
Also, looking at the visualization (attached) I feel like there is a need for reducing the individually computed (folded) partitions into a single DF. How do I do this?
#! /usr/bin/env python
# Start dask scheduler and workers
# dask-scheduler &
# dask-worker --nthreads 1 --nprocs 6 --memory-limit 3GB localhost:8786 --local-directory /dev/shm &
from dask.distributed import Client
from dask.delayed import delayed
import pandas as pd
import numpy as np
import dask.dataframe as dd
import math
foldbucketsecs=30
periodicitysecs=15
secsinday=24 * 60 * 60
chunksizesecs=60 # 1 minute
numts = 5
start = 1525132800 # 01/05
end = 1525132800 + (3 * 60) # 3 minute
c = Client('127.0.0.1:8786')
def fold(df, start, bucket):
return df
def reduce_folds(df):
return df
def load(epoch):
idx = []
for ts in range(0, chunksizesecs, periodicitysecs):
idx.append(epoch + ts)
d = np.random.rand(chunksizesecs/periodicitysecs, numts)
ts = []
for i in range(0, numts):
tsname = "ts_%s" % (i)
ts.append(tsname)
gts.append(tsname)
res = pd.DataFrame(index=idx, data=d, columns=ts, dtype=np.float64)
res.index = pd.to_datetime(arg=res.index, unit='s')
return res
gts = []
load(start)
cols = len(gts)
idx1 = pd.DatetimeIndex(start=start, freq=('%sS' % periodicitysecs), end=start+periodicitysecs, dtype='datetime64[s]')
meta = pd.DataFrame(index=idx1[:0], data=[], columns=gts, dtype=np.float64)
dfs = [delayed(load)(fn) for fn in range(start, end, chunksizesecs)]
from_delayed = dd.from_delayed(dfs, meta, 'sorted')
nfolds = int(math.ceil((end - start)/foldbucketsecs))
cprime = nfolds * cols
gtsnew = []
for i in range(0, cprime):
gtsnew.append("ts_%s,fold=%s" % (i%cols, i/cols))
idx2 = pd.DatetimeIndex(start=start, freq=('%sS' % periodicitysecs), end=start+foldbucketsecs, dtype='datetime64[s]')
meta = pd.DataFrame(index=idx2[:0], data=[], columns=gtsnew, dtype=np.float64)
folded_df = from_delayed.map_partitions(delayed(fold)(from_delayed, start, foldbucketsecs), meta=meta)
result = c.submit(reduce_folds, folded_df)
c.gather(result).visualize(filename='/usr/share/nginx/html/svg/df4.svg')
res = c.gather(result).compute()
for f in res:
f.compute()
Never mind! It was my fault, instead of wrapping my function in delayed I simply passed it to the map_partitions call like so and it worked.
folded_df = from_delayed.map_partitions(fold, start, foldbucketsecs, nfolds, meta=meta)