rohithteja

import optuna
from xgboost import XGBClassifier
from optuna.trial import TrialState
from sklearn.metrics import accuracy_score

# optuna's objective function
def objective(trial):
  learning_rate = trial.suggest_float("learning_rate", 1e-5, 1e-1, log=True)
  max_depth = trial.suggest_int("max_depth", 2, 10,step=2, log=False)
  n_estimators = trial.suggest_int("n_estimators", 100, 300,step=100, log=False)

rohithteja

from ge import DeepWalk

# load graph from networkx library
G = nx.karate_club_graph()

labels = np.asarray([G.nodes[i]['club'] != 'Mr. Hi' for i in G.nodes]).astype(np.int64)

# convert nodes from int to str format
keys = np.arange(0,34)
values = [str(i) for i in keys]

rohithteja

import plotly.express as px
import imageio

# removing small countries and NA values
geo = shapefile.dropna()
geo = geo.reset_index(drop=True)
geo = geo[['iso3','name','geometry']]

# appending temperature values to geo DF
for i in range(df_temp.shape[0]):

rohithteja

import contextily as cx

# read data
df =  gpd.read_file('data/arrondissements/arrondissements.shp',encoding='utf-8')
df = df.to_crs(epsg=3857)

fig, ax = plt.subplots(1, figsize=(10, 6),dpi=300,facecolor='w',edgecolor='w')
# colorbar
divider = make_axes_locatable(ax)
cax = divider.append_axes('right', size='5%', pad=0.3)

rohithteja

df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/fips-unemp-16.csv", dtype={"fips": str})
df.rename(columns={'fips':'GEOID'}, inplace=True)

# read US county shapefile
county_map = gpd.read_file('data/cb_2018_us_county_500k/cb_2018_us_county_500k.shp')
county_map = county_map[~county_map.STATEFP.isin(['02','15','72','60','66','69','78','11'])]
county_map = county_map.to_crs("EPSG:2163")

# read US state shapefile
state_map = gpd.read_file('data/cb_2018_us_state_500k/cb_2018_us_state_500k.shp')

rohithteja

import pandas as pd
import geopandas as gpd
import matplotlib.pyplot as plt
from mpl_toolkits.axes_grid1 import make_axes_locatable

# read data
df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2011_us_ag_exports.csv')
df.rename(columns={'code':'STUSPS'}, inplace=True)

# read US state shapefile

rohithteja

import pandas as pd
import geopandas as gpd
import plotly.express as px

# read data
df = pd.read_csv('data/population.csv',header=2)
df.rename(columns={'Country Code':'iso3'}, inplace=True)
# read shapefile
map = gpd.read_file('data/world-administrative-boundaries/world-administrative-boundaries.shp')
# merge df and shapefile 

rohithteja

import torch
import pandas as pd
from torch_geometric.data import InMemoryDataset, Data
from sklearn.model_selection import train_test_split
import torch_geometric.transforms as T

# custom dataset
class KarateDataset(InMemoryDataset):
    def __init__(self, transform=None):
        super(KarateDataset, self).__init__('.', transform, None, None)

rohithteja

import networkx as nx
import numpy as np
import torch
from sklearn.preprocessing import StandardScaler

# load graph from networkx library
G = nx.karate_club_graph()

# retrieve the labels for each node
labels = np.asarray([G.nodes[i]['club'] != 'Mr. Hi' for i in G.nodes]).astype(np.int64)

rohithteja

import optuna
from optuna.trial import TrialState
from sklearn.metrics import accuracy_score

def objective(trial):
  optimizer_name = trial.suggest_categorical("optimizer", ["adam", "SGD", "RMSprop", "Adadelta"])
  epochs = trial.suggest_int("epochs", 5, 15,step=5, log=False)
  batchsize = trial.suggest_int("batchsize", 8, 40,step=16, log=False)

  history, model = lstm(optimizer_name,epochs,batchsize)