def _rec_inner_join_helper(keycols, arr_list):
'''All the dtype-wrangling and assertions for rec_inner_join'''
assert len(arr_list), 'You must pass a string and one or more record arrays!'
assert len(set(keycols)) == len(keycols), 'keycols must not contain duplicates!'
#if jointype not in ['inner', 'outer', 'left']:
# msg = '{} jointype is not implemented. Only inner, outer, and left join are implemented.'
# raise Exception(msg.format(jointype))
names_list = [a.dtype.names for a in arr_list]
dtypes_list = lmap(get_rec_dtypes, arr_list)
names_and_dtypes_list = [lzip(names, dtypes)
for names, dtypes in zip(names_list, dtypes_list)]
_nd_dict = dict(zip(names_list[0], dtypes_list[0]))
key_dtypes = [_nd_dict[name] for name in keycols]
non_key_names_and_dtypes = [[(name, dt) for name, dt in name_dtype_list
if name not in keycols]
for name_dtype_list in names_and_dtypes_list]
non_key_col_names = fL(non_key_names_and_dtypes)[:, :, 0]
non_key_dtypes = fL(non_key_names_and_dtypes)[:, :, 1]
output_dtype = lzip(keycols, key_dtypes) + flatten(non_key_names_and_dtypes)
# Assertions to ensure bad things can't happen:
msg = 'Each input array must have all the keycols'
assert all([not (set(keycols) - set(arr.dtype.names)) for arr in arr_list]), msg
msg = 'All arrays must have the same dtype for all keycols and may not share any other columns in common'
_all_names = flatten(names_list)
expected_num_cols = len(_all_names) - len(keycols) * (len(arr_list) - 1)
assert expected_num_cols == len(output_dtype) == len(set(_all_names)), msg
return non_key_col_names, output_dtype
def zipIntoPairs(l, cycle=False, offset=1):
'''Form all adjacent pairs from a list
If cycle is True, pair the end and beginning as well
If offset is greater than 1, pair separated elements'''
if cycle:
return lzip(l, roll(l, -offset))
else:
return lzip(l[:-offset], l[offset:])
def zipIntoPairs(l,cycle=False,offset=1):
'''Form all adjacent pairs from a list
If cycle is True, pair the end and beginning as well
If offset is greater than 1, pair separated elements'''
if cycle:
return lzip(l,roll(l,-offset))
else:
return lzip(l[:-offset],l[offset:])
def infer_transition_matrix_coefficient_from_data(
self,
source: str,
target: str,
state: Optional[str] = None,
crop: Optional[str] = None,
):
""" Infer the distribution of a particular transition matrix
coefficient from data.
Args:
source: The source of the edge corresponding to the matrix element
to infer.
target: The target of the edge corresponding to the matrix element
to infer.
state:
The state in South Sudan for which the transition matrix
coefficient should be calculated.
crop:
The crop for which the transition matrix coefficient should be
calculated.
"""
rows = engine.execute(
f"select * from dssat where `Crop` like '{crop}'"
f" and `State` like '{state}'"
)
xs, ys = lzip(*[(r["Rainfall"], r["Production"]) for r in rows])
xs_scaled, ys_scaled = xs / np.mean(xs), ys / np.mean(ys)
p, V = np.polyfit(xs_scaled, ys_scaled, 1, cov=True)
self.edges[source, target]["βs"] = np.random.normal(
p[0], np.sqrt(V[0][0]), self.res
)
self.sample_from_prior()
def _rec_inner_join_helper(keycols, arr_list):
'''All the dtype-wrangling and assertions for rec_inner_join'''
assert len(
arr_list), 'You must pass a string and one or more record arrays!'
assert len(
set(keycols)) == len(keycols), 'keycols must not contain duplicates!'
#if jointype not in ['inner', 'outer', 'left']:
# msg = '{} jointype is not implemented. Only inner, outer, and left join are implemented.'
# raise Exception(msg.format(jointype))
names_list = [a.dtype.names for a in arr_list]
dtypes_list = lmap(get_rec_dtypes, arr_list)
names_and_dtypes_list = [
lzip(names, dtypes) for names, dtypes in zip(names_list, dtypes_list)
]
_nd_dict = dict(zip(names_list[0], dtypes_list[0]))
key_dtypes = [_nd_dict[name] for name in keycols]
non_key_names_and_dtypes = [[(name, dt) for name, dt in name_dtype_list
if name not in keycols]
for name_dtype_list in names_and_dtypes_list]
non_key_col_names = fL(non_key_names_and_dtypes)[:, :, 0]
non_key_dtypes = fL(non_key_names_and_dtypes)[:, :, 1]
output_dtype = lzip(keycols,
key_dtypes) + flatten(non_key_names_and_dtypes)
# Assertions to ensure bad things can't happen:
msg = 'Each input array must have all the keycols'
assert all([not (set(keycols) - set(arr.dtype.names))
for arr in arr_list]), msg
msg = 'All arrays must have the same dtype for all keycols and may not share any other columns in common'
_all_names = flatten(names_list)
expected_num_cols = len(_all_names) - len(keycols) * (len(arr_list) - 1)
assert expected_num_cols == len(output_dtype) == len(set(_all_names)), msg
return non_key_col_names, output_dtype
def fill_and_plot(points, color_code):
xs, ys = lzip(*points)
ax.plot(xs, ys, linewidth=0.5, color="grey")
ax.fill(xs, ys, color=colors[color_code])
def process_FEWSNET_IPC_data(shpfile: str, title: str):
admin_boundaries_shapefile = "data/FEWSNET_World_Admin/FEWSNET_Admin2"
sf_admin = shapefile.Reader(admin_boundaries_shapefile)
colors = {
0: "white",
1: "#c3e2c3",
2: "#f3e838",
3: "#eb7d24",
4: "#cd2026",
5: "#5d060c",
66: "aqua",
88: "white",
99: "white",
}
sf = shapefile.Reader(shpfile)
fig, ax = plt.subplots(figsize=(12, 12))
ax.set_aspect("equal")
ax.set_title(title)
plt.style.use("ggplot")
def fill_and_plot(points, color_code):
xs, ys = lzip(*points)
ax.plot(xs, ys, linewidth=0.5, color="grey")
ax.fill(xs, ys, color=colors[color_code])
fs_polygons = []
for i, sr in tqdm(enumerate(sf.shapeRecords())):
nparts = len(sr.shape.parts)
parts, points = sr.shape.parts, sr.shape.points
CS = int(sr.record[0])
if nparts == 1:
# fill_and_plot(points, CS)
fs_polygons.append((Polygon(points), int(sr.record[0])))
else:
for ip, part in enumerate(parts):
if ip < nparts - 1:
i1 = parts[ip + 1] - 1
else:
i1 = len(points)
# fill_and_plot(points[part : i1 + 1], CS),
fs_polygons.append(
(Polygon(points[part : i1 + 1]), int(sr.record[0]))
)
south_sudan_srs = [
sr for sr in sf_admin.shapeRecords() if sr.record[3] == "South Sudan"
]
lines = []
for sr in tqdm(south_sudan_srs, desc="South Sudan Counties"):
county_polygon = Polygon(sr.shape.points)
for fs_polygon in tqdm(fs_polygons, desc="fs_polygons"):
if county_polygon.buffer(-0.05).intersects(fs_polygon[0]):
centroid = county_polygon.centroid
ax.text(
centroid.x,
centroid.y,
sr.record[8],
fontsize=6,
horizontalalignment="center",
)
xs, ys = lzip(*sr.shape.points)
CS = int(fs_polygon[1])
fill_and_plot(sr.shape.points, CS)
lines.append(
"\t".join([str(x) for x in sr.record] + [str(CS)])
)
with open("ipc_data.tsv", "w") as f:
f.write("\n".join(lines))
plt.savefig("shape.pdf")
def ziptranspose(l):
'''Tranpose the two outer dimensions of a nest list
(This is just a wrapper around zip(*l) that returns a list)'''
return lzip(*l)
def ziptranspose(l):
'''Tranpose the two outer dimensions of a nest list
(This is just a wrapper around zip(*l) that returns a list)'''
return lzip(*l)
def fill_and_plot(points, sr):
xs, ys = lzip(*points)
ax.plot(xs, ys, linewidth=0.5, color="grey")
ax.fill(xs, ys, color=colors[int(sr.record[0])])
