##############################################################################
##############################################################################
csv_path = "../csv/"
in_csv_names = [
"r125-density-iter" + str(i) + "-results.csv"
for i in range(1, iternum + 1)
]
# Read files
df_csvs = [
pd.read_csv(csv_path + in_csv_name, index_col=0)
for in_csv_name in in_csv_names
]
dfs = [
prepare_df_density(df_csv, R125, liquid_density_threshold)[0]
for df_csv in df_csvs
]
def main():
#seaborn.set_palette("Set2")
seaborn.set_palette("colorblind")
# Create a dataframe with one row per parameter set
dfs_paramsets = [prepare_df_density_errors(df, R125) for df in dfs]
name = "mape_liq_density"
fig, ax = plt.subplots()
axins = inset_axes(ax,
width="100%",
]
df_csv = pd.concat(df_csvs)
df_vle = prepare_df_vle(df_csv, R125)
# Read liquid density files
max_density_iter = 4
in_csv_names = [
"r125-density-iter" + str(i) + "-results.csv"
for i in range(1, max_density_iter + 1)
]
df_csvs = [
pd.read_csv(csv_path + in_csv_name, index_col=0)
for in_csv_name in in_csv_names
]
df_csv = pd.concat(df_csvs)
df_all, df_liquid, df_vapor = prepare_df_density(df_csv, R125,
liquid_density_threshold)
### Fit GP models to VLE data
# Create training/test set
param_names = list(R125.param_names) + ["temperature"]
property_names = ["sim_liq_density", "sim_vap_density", "sim_Pvap", "sim_Hvap"]
vle_models = {}
for property_name in property_names:
# Get train/test
x_train, y_train, x_test, y_test = shuffle_and_split(
df_vle, param_names, property_name, shuffle_seed=gp_shuffle_seed)
# Fit model
vle_models[property_name] = run_gpflow_scipy(
x_train,