So I've been working on a script that a co-worker of mine made now i fixed some of his issues but i cannot seem to figure out why it only actually works when i run it in debugging mode in VSC even when i run it from a normal python shell it does not give me the output files that it does when running in debug mode does anyone know why? (Some Links and sensitive company data has been removed)
here is the code:
import requests
from requests.auth import HTTPBasicAuth
import json
import csv
import os
import pandas as pd
import datetime
import urllib3
from datetime import datetime, timedelta
#______________________________________________________________________________________
#main functie
def Main():
#http request met api account naar de export lijst Rapid7
urllib3.disable_warnings() #negeert de waarschuwingen van de self signed certificaten
url = "URL REMOVED"
r= requests.get(url,verify=False, auth=HTTPBasicAuth('REMOVED', 'REMOVED))
#data opslaan van de http request in csv formaat
with open('downloaded.csv', 'wb') as csv_file:
csv_file.write(r.content)
#open het input bestand van AD
Filenameslist = "C:\Robert-Code\ComputerListForRapid7.json" #volledig pad naar het bestand toegevoegd
with open(Filenameslist) as f:
data = json.load(f)
#converteer json naar een CSV-besand
with open("computerlist.csv", "w") as f:
fieldnames = data[3].keys()
# haal de keys van de 3e regel, want soms is de eerste regel van de sourcefile leeg
writer = csv.DictWriter(f, fieldnames=fieldnames)
writer.writeheader()
for row in data:
writer.writerow(row)
#Ik gebruik de Pandas module om alleen de kolom "name" van het Rapid7 bestand te krijgen die ik nodig heb.
# Dan draai ik naam en adres om, zodat de naam in de eerste kolom staat. Hiervoor lees ik de CSV in een dataframe
dfR7 = pd.read_csv("downloaded.csv")
titles = list(dfR7.columns)
titles[0],titles[1] = titles[1],titles[0] #draai om, zodat name in de eerste kolom staat
dfR7 = dfR7[titles] # zet de kolommen en data goed in het object
dfR7.sort_values(["Name"], inplace = True)
dfR7.drop(columns=["Address","Operating System","Site","Exploits","Malware","Vulnerabilities","Risk","Last Scan","Assessed"], inplace=True)
dfR7["Name"] = dfR7["Name"].str.split('.').str[0] #strip het domein van het FQDN
dfR7["Name"] = dfR7["Name"].str.lower() # alles lowercase
#Pandas module om ook van het AD-betand 1 kolom "name" over te houden in het object dfAD zodat ik later kan vergelijken.
dfAD = pd.read_csv("computerlist.csv")
dfAD.drop(columns=["DNSHostName","OperatingSystem","IPAddress", "LastLogon"], inplace= True)
dfAD["Computer"] = dfAD["Computer"].str.lower()
#beide objecten opslaan in een csv-bestand deze te vergelijken
dfR7.to_csv("fr7.csv", index=False)
dfAD.to_csv("fAD.csv", index=False)
with open('fr7.csv', 'r') as t1, open('fAD.csv', 'r') as t2:
fileRapid = t1.readlines()
fileAD = t2.readlines()
#de bestanden fr7.csv en fad.csv vergelijken aan de hand van een for loop
# deze dan opslaan in update.csv
with open('update.csv', 'w') as outFile:
for line in fileAD:
if line not in fileRapid:
outFile.write(line)
#hier haal ik weer het oude bestand van AD erbij om deze zometeen te mergen met het net gemaakte update.csv bestand
# zodat ik alle nuttige kolommen weer heb
dfAD = pd.read_csv("computerlist.csv")
dfAD["Computer"] = dfAD["Computer"].str.lower()
dfAD.to_csv("f1AD.csv", index=False)
# merge functie van de Pandas module
data1 = pd.read_csv('update.csv')
data2 = pd.read_csv("f1AD.csv")
output1 = pd.merge(data1, data2,
on='Computer',
how='inner')
#opslaan naar TotalresultsAD.csv
output1.to_csv("totaldifferenceAD_R7.csv", index =False)
#met de datetime module maak ik een variabele: time met de dag van vandaag minus 30 dagen
time = datetime.today() - timedelta(60)
"lees 2 x het bestand in"
dfgood = pd.read_csv("totaldifferenceAD_R7.csv")
dfbad = pd.read_csv("totaldifferenceAD_R7.csv")
#dit outputbestand geeft de assets weer die een LastLogon hebben recenter dan 30 dagen geleden
dfgood['LastLogon'] = pd.to_datetime(dfgood['LastLogon'], errors = 'coerce') #errors = 'coerce' zorgt ervoor dat de foutieve waarden in de kolom LastLogon worden genegeerd
dfgood.sort_values(["LastLogon"], inplace = True)
dfnew = (dfgood['LastLogon'] >= time)
dfnew = dfgood.loc[dfnew]
#dit outputbestand geeft de assets weer die een LastLogon hebben ouder dan 30 dagen geleden
dfbad['LastLogon'] = pd.to_datetime(dfbad['LastLogon'], errors = 'coerce') #errors = 'coerce' zorgt ervoor dat de foutieve waarden in de kolom LastLogon worden genegeerd
dfbad.sort_values(["LastLogon"], inplace = True)
newdf2 = (dfbad['LastLogon'] < time)
newdf2 = dfbad.loc[newdf2]
#wegschrijven uiteindelijke bestanden
dfnew.to_csv("newer_than_60_days.csv",index =False)
newdf2.to_csv("older_than_60_days.csv",index =False)
#opschonen van de bestanden
os.remove("FAD.csv")
os.remove("fr7.csv")
os.remove("computerlist.csv")
os.remove("downloaded.csv")
os.remove("f1AD.csv")
os.remove("update.csv")
if __name__=="__main__":
Main() ```
Thanks in advance for any help
Because I don't have a high enough SO reputation, unfortunately I can't simply comment this and need to make it an 'Answer'.
Changing
r= requests.get(url,verify=False, auth=HTTPBasicAuth('REMOVED', 'REMOVED))
to
r= requests.get(url,verify=False, auth=HTTPBasicAuth('REMOVED', 'REMOVED'))
will get the syntax highlighting all fixed up and may make it easier for someone smarter than me to assist you :)
Something that I've previously come across (primarily with web scraping packages) were functions that didn't play nicely with relative paths - perhaps changing them to absolute paths using os.path.abspath(".....") may help? It's a stab in the dark so that this 'Answer' actually has a potentially useful element to it, but may be an adjustment worth exploring.
Related
I have a small big problem with an app I have created, using Python and Streamlit.
The problem is that when I want to deploy it to the Heroku services, it builds, but when I try to access it, it tells me that there is an applicaiton error.
I have looked at my code, whcih on the local machine works pefectly.
Do you have any idea?
Code:
# Loading packages ##########################################################################
import streamlit as st
import numpy as np
import networkx as nx
from pyvis.network import Network
# import plotly.express as px
###############################################################################################
st.set_page_config(layout="wide")
##### Creazione Sidebar ####################################################################
st.sidebar.title('Ottimizzazione')
st.sidebar.header('Creazione matrice')
st.sidebar.write('Scrivere la matrice quadrata come da esempio Matrice: 1,2;4,5')
st.sidebar.write('Usare la , per separe le varie colonne e il ; per andare alla prossima riga')
input_matrice=st.sidebar.text_area('Scrivere Matrice:')
# Creazione matrice
matrice = np.matrix(input_matrice)
matrice_array = np.asarray(matrice)
##### Creazione Due colonne per output ##############################################################
left_column1, right_column1 = st.beta_columns(2)
left_column2, right_column2 = st.beta_columns(2)
## Visualizzazione matrice
with left_column1:
st.header('Matrice Quadrata Creata:')
matrice_array
with right_column1:
st.header('Visualizzazione del grafo:')
st.write('Il grafo verrà visualizzato in una apgina separata, in quanto al momento non riuslta possible integrarlo nella pagina pricipale')
##### Creaizone Input per calcolo #######################################################
st.sidebar.header('Calcolo percorso:')
st.sidebar.write('Calcolo del percorso più corto, Nx nodo di partenza e Ny nodo di arrivo. I nodi della matrice corrispondono agli indici della colonna.')
selezione = st.sidebar.radio("Seleziona tipo di calcolo",('Da Nx a tutti più vicini','Da Nx a Ny'))
if selezione == 'Da Nx a tutti più vicini':
nodo_partenza=np.int(st.sidebar.number_input('Scrivere nodo di partenza (Numero intero):'))
bottone_calcolo = st.sidebar.button('Calcola percorso', key=1)
if bottone_calcolo:
grafo_matrice = nx.from_numpy_matrix(matrice_array)
percorso = nx.single_source_dijkstra_path(grafo_matrice, nodo_partenza, weight='weight')
lunghezza = nx.single_source_dijkstra_path_length(grafo_matrice, nodo_partenza, weight='weight')
with left_column2:
st.header('Percorsi:')
st.write('Qui vengono mostrati i vari percorsi che sono stati trovati. I valori a destra corrispondono al ordine di successione, mentre I valori a destra i vari nodi.')
percorso
with right_column2:
st.header('Tempi percorsi:')
st.write('Qui vengono mostrati i vari tempi dei vari percorsi')
lunghezza
with right_column1:
nt=Network("1000px","1000px")
nt.from_nx(grafo_matrice)
nt.show("nx.html")
elif selezione == 'Da Nx a Ny':
nodo_partenza=np.int(st.sidebar.number_input('Scrivere nodo di partenza (Numero intero):'))
nodo_arrivo=np.int(st.sidebar.number_input('Scrivere nodo di arrivo (Numero intero):'))
bottone_calcolo = st.sidebar.button('Calcola percorso', key=2)
if bottone_calcolo:
grafo_matrice = nx.from_numpy_matrix(matrice_array)
percorso = nx.shortest_path(grafo_matrice, source=nodo_partenza, target=nodo_arrivo, weight='weight')
lunghezza = nx.shortest_path_length(grafo_matrice, source=nodo_partenza, target=nodo_arrivo, weight='weight')
with left_column2:
st.header('Percorso:')
st.write('Qui viene mostrato il percorso trovato. I valori a destra corrispondono al ordine di successione, mentre I valori a destra i vari nodi.')
percorso
with right_column2:
st.header('Tempo percorso:')
st.write('Qui viene mostrato il tempo totale del pecrorso più breve')
lunghezza
with right_column1:
nt=Network("1000px","1000px")
nt.from_nx(grafo_matrice)
nt.show("nx.html")
Requirements:
streamlit==0.75.0
numpy==1.19.2
networkx==2.5.0
pyvis==0.1.9
Thank you for the help!
I solved the issue, it appear the problem was not in the code, but inside the command of the code for running the webapp
I'm having trouble displaying some data from Globcolour (1), due to the projection used with the matplotlib and cartopy definition of the image.
I downloaded a Total Suspended Matter image in NetCDF format (here is the data enter link description here), and when I tried to display it, along with a coastline from the cartopy package, there is a notorious gap between the coastline and the data. As you can see below, the pixels should be next to the coastline (black line), and not surpassed into the land (yellow pixels in the flags image)
This shouldn't happen. I check using QGIS and loading directly the netcdf file the coastline is set correctly.
Initially I used a PlateeCarrer projection for the image, considering that if the image was in WGS84 they would match, but clearly they don't. I've tried using the transform option in the matplotlib function but I haven't made it work. Either the gap remains, or the coordinates of the figure change to projected ones and my data (which is in geographical coordinates) disappear.
The attributes of the NetCDF file are:
'grid_type': 'Equirectangular',
'spatial_resolution': 4.6383123,
'nb_equ_bins': 55,
'registration': 5,
'lat_step': 0.041666668,
'lon_step': 0.041666668,
'earth_radius': 6378.137,
'max_north_grid': 11.124998,
'max_south_grid': 9.27,
'max_west_grid': -86.25,
'max_east_grid': -83.97,
'northernmost_latitude': 11.124998,
'southernmost_latitude': 9.249998,
'westernmost_longitude': -86.25,
'easternmost_longitude': -84.0,
'nb_grid_bins': 2475,
'nb_bins': 2475,
'pct_bins': 100.0,
'nb_valid_bins': 1089,
'pct_valid_bins': 44.0,
'netcdf_version': '4.3.3.1 of Jul 8 2016 18:15:50 $',
'DPM_reference': 'GC-UD-ACRI-PUG',
'IODD_reference': 'GC-UD-ACRI-PUG'}
The code that I'm using to plot the image is:
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
import cartopy.crs as ccrs
import dill as pickel
def paint_maps(df_std=None, fecha=1, attributes=None,
savefol='/media/felipe/TOSHIBA EXT/iMARES/Investigacion/2019_MariculturaPacifico/DB/figures/',
disp_fig=0):
"""Función para dibujar los datos contenidos en los archivos netCDF de SST, Salinidad y propiedad ópticas del agua.
Recibe el dataframe con la información en formato de Pandas Dataframe, y selecciona según una fecha establecida,
el conjunto de datos con coordenadas Lat-Lon que debe dibujar. Esos los dibuja y transforma a formato raster. Unido
se dibuja también la línea de costa proveniente de un archivo shapefile. La función dibuja toda la información
contenida en el dataframe aportado (datos, anomalías, flags, y cualquier otro dato que tenga.
Recibe:
df_std: dataframe con la información a dibujar. Debe venir indexado por fecha, lat y lon.
fecha: día que se elige dibujar. Formato string 'yyyymmdd'. Valor 1 significa que grafica el valor promedio de todas las fechas en cada
píxel. Promedio simple ignorando NaN's
attributes: diccionario con los atributos del netcdf de donde se obtiene nombre de variable y unidades. Creado
con open_netcdf.py
savefol: carpeta donde se guardan las imágenes dibujadas
disp_fig: booleano para imprimir figura en pantalla.
Devuelve:
Nada. Solo crea y guarda figuras"""
# Identifica la fecha solicitada (cuando se ha especificado) y confirma que sea parte del registro. Extrae la
# información del Dataframe en la fecha que se solicitó, o calcula el promedio de todas las fechas para graficar
# el valor promedio.
if fecha != 1:
if isinstance(fecha, str):
fecha = pd.to_datetime(fecha + '120000')
else:
print('La fecha indicada no está en formato String. Reinicie la ejecución.')
try:
idx = pd.IndexSlice
df_map = df_std.loc[idx[:, :, fecha], :]
except:
print('Se generó un error. Posiblemente fecha no está dentro del registro. La fecha debe estar entre el ' + df_std.index[0][-1].strftime('%d/%m/%Y') + ' y el ' + df_std.index[-1][-1].strftime('%d/%m/%Y'))
raise
else:
df_map = df_std.groupby(['lat', 'lon']).mean()
# Reestructura la información para tenerla en forma de matriz y dibujarla de forma más simple. Extrae los valores y
# las latitudes y longitudes correspondientes, así como los valores de la variable y sus flags.
df_map2 = df_map.unstack(level=0)
vari = df_map2['mean_val'].values
flags = df_map2['flag_val'].values
lat = df_map2['mean_val'].columns.get_level_values('lat')
lon = df_map2['mean_val'].index.get_level_values('lon')
# Extrae de los atributos del netcdf el nombre de la variable a graficar y las unidades
variable_str = attributes['variable']['long_name']
variable_units = attributes['variable']['units']
# Dibuja el mapa que se haya seleccionado según fecha (valor promedio del valor o fecha específica)
fig, ax = plt.subplots(1, 2, figsize=(10, 10), subplot_kw={'projection': ccrs.PlateCarree()})
extend = [lon[1], lon[-1], lat[1], lat[-1]]
# Primera figura. Variable a graficar. Usa línea de costa del cartopy y coloca una leyenda abajo
ax[0].set_extent(extend)
ax[0].coastlines(resolution='10m')
#cs = ax[0].pcolormesh(lon, lat, vari.T)
cs = ax[0].pcolormesh(lon, lat, vari.T, transform=ccrs.PlateCarree())
ax[0].set_title(variable_str)
cax, kw = matplotlib.colorbar.make_axes(ax[0], location='bottom', pad=0.05, shrink=0.7)
out = fig.colorbar(cs, cax=cax, extend='both', **kw)
out.set_label('Units: '+variable_units, size=10)
# Segunda figura. Flags de la figura. Usa la leyenda directamente de los datos usados.
ax[1].set_extent(extend)
ax[1].coastlines(resolution='10m')
cs2 = ax[1].pcolormesh(lon, lat, flags.T)
ax[1].set_title('Flags')
cax, kw = matplotlib.colorbar.make_axes(ax[1], location='bottom', pad=0.05, shrink=0.7)
out = fig.colorbar(cs2, cax=cax, extend='both', **kw)
out.set_label('Flags', size=10)
# Salva la figura
plt.savefig(savefol+variable_str+'.jpg', bbox_inches='tight')
with open(savefol+'fig_'+variable_str+'.pickel', 'wb') as f:
pickel.dump(fig, f)
# Imprime figura si se elige opción con disp_fig
if disp_fig == 1:
plt.show()
return
It receives the data as a Pandas dataframe. The NetCDF was opened using xarray.open_dataset and then transforming it to Pandas with to_dataframe()
I'm using Python 3.7 in Ubuntu.
Last thing. When loading the cartopy.crs package, this error occurs:
ERROR 1: PROJ: proj_create_from_database: Open of /home/felipe/anaconda3/envs/personal/share/proj failed
Could it be affecting?
we answered to Felipe by email, I copy/paste here:
A small Python script to create a map on your area from a TSM GlobColour Product (I used a monthly product to have a good coverage):
import netCDF4 as nc
import numpy as np
import matplotlib.pyplot as plt
import cartopy.crs as ccrs
fig, ax = plt.subplots(figsize=(5, 5), subplot_kw=dict(projection=ccrs.PlateCarree()))
# my region of interest
ax.set_extent([-86, -84, 9, 11])
ax.coastlines(resolution='10m', color='red')
nc_dst = nc.Dataset('L3m_20100101-20100131__GLOB_4_AV-MER_TSM_MO_00.nc')
# extent of the product
data_extent = [nc_dst.max_west_grid, nc_dst.max_east_grid,
nc_dst.max_south_grid, nc_dst.max_north_grid]
data = nc_dst.variables['TSM_mean'][:]
flags = nc_dst.variables['TSM_flags'][:]
land = flags & 8 # LAND == 3rd bit == 2^3 == 8
data_noland = np.ma.masked_where(land, data)
ax.imshow(data_noland, origin='upper', extent=data_extent)
plt.savefig('TSM_noland.png')
ax.imshow(data, origin='upper', extent=data_extent)
plt.savefig('TSM.png')
I think you are facing to 2 problems:
1) Our products may overlap some land areas because of the Level-3 rebinning during the GlobColour processing: if a 4km pixel has only the corner on the water we will fill the full pixel. We keep them because they may be usefull for some needs (for example areas where the land/water limit is varying), but in the quality flags we provide a LAND mask which could be used to remove these pixels. You can also use your own LAND mask if you prefer. The Python example below shows how to use the LAND mask.
2) I suspect that your Python code introduces an east/south shift of at least half a pixel maybe because the lat/lon arrays are for the center of each pixel but the extent needed by cartopy is the exterior limit.
GlobColour flags are defined in the Product User Guide http://www.globcolour.info/CDR_Docs/GlobCOLOUR_PUG.pdf page 76.
The GlobColour Team
Are you sure your data are in WGS84? Looking at the metadata, I only see:
'earth_radius': 6378.137
which I imply means assume a spherical Earth with radius 6378.137 km. I don't have access to your data, but I would try setting up a cartopy.crs.Globe instance with that radius.
I'm working on old French Napoleonian cadastre, I've vectorized it, and now I've been studying parcels' neighborhood relation. I want to know which polygon is next to which polygon.
I tried NetworkX python library, but I did not succeed to convert my shapefile to a graph. I want to extract centroids from my polygons and trace relation between them.
I can use line shapefile or area shapefile to represent my parcels.
There is my python code:
import networkx as nx
import matplotlib.pyplot as plt
G=nx.read_shp('path/to/shp') #Read shapefile as graph
pos = {xy: xy for xy in G.nodes()}
nx.draw_networkx_nodes(G,pos,node_size=10,node_color='r')
nx.draw_networkx_edges(G,pos,edge_color='b')
plt.show()
This is my shapefile:
All right, I've fixed my problem with PySal library.
There is my code if someone need to generate some graphs!
##Définition des relations d'adjacence
qW = ps.queen_from_shapefile(str(planche)+".shp")
dataframe = ps.pdio.read_files(str(planche)+".shp")
## Affiche la matrice de voisinage complète.
Wmatrix, ids = qW.full() #ou ps.full(qW)
print("Matrice d'adjacence complète:\n", Wmatrix)
print("\n")
## pour compter le nombre de voisins que possède une parcelle:
n_neighbors = Wmatrix.sum(axis=1)
for i in range (len(n_neighbors)):
if n_neighbors[i] != 0:
print("La parcelle %i a %i voisins" %(i,n_neighbors[i]))
else:
print("La parcelle %i n'a pas de voisin" %i)
print("")
## Affiche [parcelle choisie, ses voisins]:
for i in range (len(n_neighbors)):
self_and_neighbors = [i]
self_and_neighbors.extend(qW.neighbors[i])
if self_and_neighbors[1:] == []:
print("La parcelle %i n'a pas de voisin" %i)
else:
print("Les voisins de la parcelle %i sont les parcelles " %i, self_and_neighbors[1:])
##Extractions des coordonnées des centroïds:
centroids = np.array([list(poly.centroid) for poly in dataframe.geometry])
plt.plot(centroids[:,0], centroids[:,1],'.')
for k,neighs in qW.neighbors.items():
#print(k,neighs)
#origin = centroids[k]
for neigh in neighs:
segment = centroids[[k,neigh]]
plt.plot(segment[:,0], segment[:,1], '-')
##Affichage des numéros des centroïds sur le graph:
for i in range (len(centroids)):
plt.text(centroids[i][0],centroids[i][1],str(i))
plt.title('Graph de la planche '+str(planche)+ " de l'année "+str(annee))
print("\nDuree: %.2f sec" %(time.time()-deb))
show()
I have a text file:
Jan Jansen heeft kaartnummer: 325255
Erik Materus heeft kaartnummer: 334343
Ali Ahson heeft kaartnummer: 235434
Eva Versteeg heeft kaartnummer: 645345
Jan de Wilde heeft kaartnummer: 534545
Henk de Vrie heeft kaartnummer: 345355
I need to print three things: the biggest int value, the number of lines and the line the biggest int is located in. I have done the first two, but I have no idea how to print the line the biggest int is located in. I hope you guys can help me.
This is what I got so far:
import re
num_lines = sum(1 for line in open("Kaartnummers.txt"))
print(num_lines)
int = open("Kaartnummers.txt", "r")
file = open("Kaartnummers.txt", "r")
file = file.read()
numbers = re.findall(r"[-+]?\d*\.\d+|\d+", file)
print(numbers)
numbers.sort()
print("The b"numbers[-1])
I know its very messy but I'm very new to coding and so I'm not very good.
Maybe this helps... A part of it uses python 3.6, but you can omit it it you have a file ready. The last few lines answer your immediate question.
import csv
from pathlib import Path
doc = """Jan Jansen heeft kaartnummer: 325255
Erik Materus heeft kaartnummer: 334343
Ali Ahson heeft kaartnummer: 235434
Eva Versteeg heeft kaartnummer: 645345
Jan de Wilde heeft kaartnummer: 534545
Henk de Vrie heeft kaartnummer: 345355"""
# recreating your file with data, python 3.6
# skip this line if you have the file already
Path("mydata.csv").write_text(doc)
with open("mydata.csv") as f:
reader = csv.reader(f)
rows = [row for row in reader]
# now you have your data inside interpreter as list of strings
print(rows)
# this seems to be common string in all the lines
sep = " heeft kaartnummer: "
# lets seperate name and values to be bale to play with them
rows2 = [row[0].split(sep) for row in rows]
print(rows2)
# lets associate the kaartnummer with a name in a dictionary
knum_dict = {int(num):name for name, num in rows2}
print(knum_dict)
#I need to print three things:
# the biggest int value,
# the number of lines
# and the line the biggest int is located in.
print()
print("Total number of lines:", len(rows))
max_num = max(knum_dict.keys())
print()
print("Biggest int:", max_num)
print("The biggest int is found for:", knum_dict[max_num])
#now back to your original quection -
#and the line the biggest int is located in
for i, row in enumerate(rows2):
if int(row[1]) == max_num:
#
print("The biggest int is found in line:", i+1)
print("(first line number is 1)"
I have a Database Class built in Python 3.5.2, which I am built to have general functions other classes could use to connect to the DB.
I am using SQLite and SQLite Studio to check my work.
So far, I have successfully created create-table functions, as well as others that return the name of all tables in the database (in a list), and one that returns the names of all columns in any table of the DB.
The problem:
For some reason, the INSERT INTO method is crashing my DB (it takes a while, then it says it's locked). It creates a db-journal file in the same folder, I assume it's some kind of log.
I have substituted the execute lines for prints, to check that the query is ok. I have got the query it prints and put it into the query editor of sqlite Studio to see if they work, AND THEY DO!
The method uses a while loop to create a query for each insert I want to do, and I am quite sure there is something wrong with my method definition. It must be doing something that crashes de DB (maybe something memory related?)
Here is the code:
import sqlite3
class Database:
def __init__(self, name):
self.name=name
self.db_conn=sqlite3.connect(self.name+'.db')
self.cursor=self.db_conn.cursor()
self.commit=self.db_conn.commit()
def get_name(self):
return self.name
def get_tableNames(self):
#get table names into a list:
self.tables=[]
c=self.db_conn.execute("select name from sqlite_master where type = 'table'")
for row in c:
self.tables.append(row[0])
return self.tables
def get_tableColumns(self,tableName):
#get table columns into a list:
self.tableName=tableName
self.columns=[]
c=self.db_conn.execute("PRAGMA table_info("+ self.tableName+" );")
for row in c:
self.columns.append(row[1])
return self.columns
def create_table(self,table_name,*args):
#crear una tabla con nombre table_name y columns= cada uno de los argumentos de *fields.
#cada campo de args debe ser una lista.
self.table_name=table_name
fields=[]
for field in args:
fields.append(field)
i=0
try:
self.db_conn.execute("CREATE TABLE " +self.table_name+ "(ID INTEGER PRIMARY KEY AUTOINCREMENT);")
self.commit
except sqlite3.OperationalError:
print("La tabla "+self.table_name+" no se ha creado")
#añadimos las columnas a la tabla creada:
while i<len(fields):
if len(fields[i])==2:
try:
self.db_conn.execute("ALTER TABLE "+self.table_name+" ADD COLUMN "+fields[i][0]+" "+fields[i][1].upper()+";")
self.commit
i+=1
except sqlite3.OperationalError:
print("No se ha podido añadir la columna "+fields[i][0]+" a la tabla "+self.table_name)
i+=1
elif len(fields[i])==3:
try:
self.db_conn.execute("ALTER TABLE " +table_name+" ADD COLUMN " +fields[i][0]+" "+fields[i][1].upper()+" ("+str(fields[i][2])+") "+";")
self.commit
i+=1
except sqlite3.OperationalError:
print("No se ha podido añadir la columna "+fields[i][0]+" a la tabla "+self.table_name)
i+=1
else:
print('los argumentos deben ser listas donde el primer elemento será el nombre de la columna y los otros dos, el tipo y tamaño (de haberlo)')
def insert(self,tableName, *vals):
#insertar valores en tabla:
fields=self.get_tableColumns(tableName)
rows=[]
for row in vals:
rows.append(row)
r=0
while r<len(rows):
i=1
query="INSERT INTO "+self.tableName+" ("
while i<len(fields):
query=query+str(fields[i]+',')
i+=1
query=query[:-1]
query=query+') VALUES ('
i=0
while i<len(rows[r]):
if type(rows[r][i]) is str:
query=query+str("'"+rows[r][i]+"'"+',')
else:
query=query+str(rows[r][i])+','
i+=1
query=query[:-1]+');'
print(query)
print('commit')
try:
self.db_conn.execute(query)
self.commit
print("se han añadido los datos a la tabla")
except sqlite3.OperationalError:
print('no se han podido añadir los valores específicos a la tabla '+self.tableName)
r+=1
#esta función peta la DB y por eso no funcionan las queries.
def close(self):
self.db_conn.close()
closed= 'database closed'
return closed
In order to make it work:
db=Database('stock-data')
db.create_table('test',['name','text',50],['age','integer'])
db.insert('test',['john',20],['will',21])
This last expression is the one that crashes.