예제 #1
0
from dask.context import config
import dask.dataframe as dd
import numpy as np
import pandas as pd
import xarray as xr

import datashader as ds

import pytest

config.set(scheduler='synchronous')

df = pd.DataFrame({'x': np.array(([0.] * 10 + [1] * 10)),
                   'y': np.array(([0.] * 5 + [1] * 5 + [0] * 5 + [1] * 5)),
                   'log_x': np.array(([1.] * 10 + [10] * 10)),
                   'log_y': np.array(([1.] * 5 + [10] * 5 + [1] * 5 + [10] * 5)),
                   'i32': np.arange(20, dtype='i4'),
                   'i64': np.arange(20, dtype='i8'),
                   'f32': np.arange(20, dtype='f4'),
                   'f64': np.arange(20, dtype='f8'),
                   'empty_bin': np.array([0.] * 15 + [np.nan] * 5),
                   'cat': ['a']*5 + ['b']*5 + ['c']*5 + ['d']*5})
df.cat = df.cat.astype('category')
df.f32[2] = np.nan
df.f64[2] = np.nan

ddf = dd.from_pandas(df, npartitions=3)

c = ds.Canvas(plot_width=2, plot_height=2, x_range=(0, 1), y_range=(0, 1))
c_logx = ds.Canvas(plot_width=2, plot_height=2, x_range=(1, 10),
                   y_range=(0, 1), x_axis_type='log')
예제 #2
0
from __future__ import division
from dask.context import config
import dask.dataframe as dd
import numpy as np
import pandas as pd
import xarray as xr

import datashader as ds
import datashader.utils as du

import pytest

config.set(scheduler='synchronous')

df = pd.DataFrame({
    'x': np.array(([0.] * 10 + [1] * 10)),
    'y': np.array(([0.] * 5 + [1] * 5 + [0] * 5 + [1] * 5)),
    'log_x': np.array(([1.] * 10 + [10] * 10)),
    'log_y': np.array(([1.] * 5 + [10] * 5 + [1] * 5 + [10] * 5)),
    'i32': np.arange(20, dtype='i4'),
    'i64': np.arange(20, dtype='i8'),
    'f32': np.arange(20, dtype='f4'),
    'f64': np.arange(20, dtype='f8'),
    'empty_bin': np.array([0.] * 15 + [np.nan] * 5),
    'cat': ['a'] * 5 + ['b'] * 5 + ['c'] * 5 + ['d'] * 5
})
df.cat = df.cat.astype('category')
df.f32[2] = np.nan
df.f64[2] = np.nan

ddf = dd.from_pandas(df, npartitions=3)
예제 #3
0
from dask.local import get_sync
from dask.context import config
import dask.dataframe as dd
import numpy as np
import pandas as pd
import xarray as xr

import datashader as ds

import pytest

config.set(scheduler=get_sync)

df = pd.DataFrame({
    'x': np.array(([0.] * 10 + [1] * 10)),
    'y': np.array(([0.] * 5 + [1] * 5 + [0] * 5 + [1] * 5)),
    'log_x': np.array(([1.] * 10 + [10] * 10)),
    'log_y': np.array(([1.] * 5 + [10] * 5 + [1] * 5 + [10] * 5)),
    'i32': np.arange(20, dtype='i4'),
    'i64': np.arange(20, dtype='i8'),
    'f32': np.arange(20, dtype='f4'),
    'f64': np.arange(20, dtype='f8'),
    'empty_bin': np.array([0.] * 15 + [np.nan] * 5),
    'cat': ['a'] * 5 + ['b'] * 5 + ['c'] * 5 + ['d'] * 5
})
df.cat = df.cat.astype('category')
df.f32[2] = np.nan
df.f64[2] = np.nan

ddf = dd.from_pandas(df, npartitions=3)