precipitation-pl/run2.py

import pandas as pd

import tensorflow.keras
from sklearn.linear_model import LinearRegression
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

import numpy as np
import pandas as pd
import xgboost as xg
from sklearn.compose import TransformedTargetRegressor
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import (
    QuantileTransformer,
    StandardScaler,
    PolynomialFeatures,
)

import tensorflow.keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
# Import the required library
from geopy.geocoders import Nominatim

# Initialize Nominatim API
geolocator = Nominatim(user_agent="MyApp")



in_columns = ["id_stacji", "nazwa_stacji", "typ_zbioru", "rok", "miesiąc"]
df = pd.read_csv("train/in.tsv", names=in_columns, sep="\t")
df_test = pd.read_csv("dev-0/in.tsv", names=in_columns, sep="\t")

df = pd.concat([df, df_test])
# df = df.drop(["nazwa_stacji"], axis=1)
x = pd.get_dummies(df, columns=["id_stacji", "rok", "miesiąc"])
# geo_lat = {
#     "BIEBRZA-PIEŃCZYKÓWEK" : 53.65
# }
# geo_long = {
#     "BIEBRZA-PIEŃCZYKÓWEK": 22.58
# }
# for xd in x["nazwa_stacji"].unique():
#     location = geolocator.geocode(xd)
#     if xd == "BIEBRZA-PIEŃCZYKÓWEK":
#         pass
#     else:
#         print(xd)
#         geo_lat[xd] = location.latitude
#         geo_long[xd] = location.longitude
#
#
# x["latitude"] = x["nazwa_stacji"].map(geo_lat)
# x["longitude"] = x["nazwa_stacji"].map(geo_long)
x = x.drop(["nazwa_stacji", "typ_zbioru"], axis=1)
poly = PolynomialFeatures(2, interaction_only=True)
#
# print(x)
# print(geo_lat)
# print(geo_long)
x = x.iloc[:-600]
x = poly.fit_transform(x)
y = pd.read_csv("train/expected.tsv", sep="\t", names=["rainfall"])


from sklearn.preprocessing import PolynomialFeatures
# xxx
# poly = PolynomialFeatures(2, interaction_only=True)
# df = poly.fit_transform(x)
param_grid = {
    "n_estimators": [100, 80, 60, 55, 51, 45],
    "max_depth": [7, 8],
    "reg_lambda": [0.26, 0.25, 0.2],
}

grid = GridSearchCV(
    xg.XGBRFRegressor(), param_grid, refit=True, verbose=3, n_jobs=-1
)  #
regr_trans = TransformedTargetRegressor(
    regressor=grid, transformer=QuantileTransformer(output_distribution="normal")
)

# fitting the model for grid search
grid_result = regr_trans.fit(x, y)
best_params = grid_result.regressor_.best_params_

# using best params to create and fit model
best_model = xg.XGBRFRegressor(
    max_depth=best_params["max_depth"],
    n_estimators=best_params["n_estimators"],
    reg_lambda=best_params["reg_lambda"],
)
regr_trans = TransformedTargetRegressor(
    regressor=best_model, transformer=QuantileTransformer(output_distribution="normal")
)

regr_trans.fit(x, y)

# model = Sequential(
#     [
#         Dense(512, activation="relu", input_dim=75),
#         tensorflow.keras.layers.BatchNormalization(),
#         Dense(512 // 2, activation="relu"),
#         tensorflow.keras.layers.BatchNormalization(),
#         Dense(512 // 4, activation="relu"),
#         tensorflow.keras.layers.BatchNormalization(),
#         Dense(512 // 8, activation="relu"),
#         tensorflow.keras.layers.BatchNormalization(),
#         Dense(32, activation="relu"),
#         tensorflow.keras.layers.BatchNormalization(),
#         Dense(1),
#     ]
# )
#
# model.compile(
#     loss="mean_squared_error", optimizer="adam", metrics=["mean_squared_error"]
# )
# model.fit(x, y, epochs=100)

x_test = pd.read_csv("test-A/in.tsv", sep="\t", names=in_columns)
df_train = pd.read_csv("train/in.tsv", names=in_columns, sep="\t")

# geo_lat = {
#     "BIEBRZA-PIEŃCZYKÓWEK" : 53.65
# }
# geo_long = {
#     "BIEBRZA-PIEŃCZYKÓWEK": 22.58
# }
x_test = pd.concat([x_test, df_train])

# for xd in x_test["nazwa_stacji"].unique():
#     location = geolocator.geocode(xd)
#     if xd == "BIEBRZA-PIEŃCZYKÓWEK":
#         pass
#     else:
#         print(xd)
#         geo_lat[xd] = location.latitude
#         geo_long[xd] = location.longitude
#
#
# x_test["latitude"] = x_test["nazwa_stacji"].map(geo_lat)
# x_test["longitude"] = x_test["nazwa_stacji"].map(geo_long)

x_test = x_test.drop(["nazwa_stacji", "typ_zbioru"], axis=1)
x_test = pd.get_dummies(x_test, columns=["id_stacji", "rok", "miesiąc"])
poly = PolynomialFeatures(2, interaction_only=True)
x_test = x_test.iloc[:-8760]
x_test = poly.fit_transform(x_test)
# poly = PolynomialFeatures(2, interaction_only=True)
# x_test2 = poly.fit_transform(x_test)
# pred = model.predict(x_test)
test_A_predicted = regr_trans.predict(x_test)


out = pd.DataFrame(test_A_predicted)
out.to_csv("test-A/out.tsv", sep="\t", header=False, index=False)