From 7dfdc7daaefae28468ef3b12703cd85cb40bd607 Mon Sep 17 00:00:00 2001
From: Knut Rand <knutdrand@gmail.com>
Date: Fri, 20 Sep 2024 11:27:52 +0200
Subject: [PATCH] feature: weekly predictions ahead in time

---
 climate_health/assessment/forecast.py         | 16 ++--
 .../assessment/prediction_evaluator.py        |  7 +-
 climate_health/climate_predictor.py           | 24 ++++--
 .../temporal_dataclass.py                     |  5 +-
 climate_health/time_period/__init__.py        |  2 +-
 .../time_period/date_util_wrapper.py          | 71 +++++++++++++----
 pytest.ini                                    |  2 +-
 scripts/clean_laos_data2.py                   | 77 ++++++++++++-------
 scripts/evaluate_laos.py                      | 12 +++
 scripts/prediction_example.py                 | 17 +++-
 tests/test_climate_predictor.py               | 19 ++++-
 tests/test_forecast.py                        |  9 ++-
 tests/time_period/test_dateutil_wrapper.py    |  2 +-
 13 files changed, 194 insertions(+), 69 deletions(-)
 create mode 100644 scripts/evaluate_laos.py

diff --git a/climate_health/assessment/forecast.py b/climate_health/assessment/forecast.py
index ef162900..28f62750 100644
--- a/climate_health/assessment/forecast.py
+++ b/climate_health/assessment/forecast.py
@@ -3,7 +3,7 @@
 
 from climate_health.assessment.dataset_splitting import train_test_split_with_weather
 from climate_health.assessment.prediction_evaluator import Estimator, Predictor
-from climate_health.climate_predictor import MonthlyClimatePredictor
+from climate_health.climate_predictor import MonthlyClimatePredictor, get_climate_predictor
 from climate_health.data.gluonts_adaptor.dataset import ForecastAdaptor
 from climate_health.plotting.prediction_plot import plot_forecast_from_summaries
 from climate_health.spatio_temporal_data.temporal_dataclass import DataSet
@@ -60,10 +60,16 @@ def forecast_ahead(estimator: Estimator, dataset: DataSet, prediction_length: in
 
 
 def forecast_with_predicted_weather(predictor: Predictor, historic_data: DataSet, prediction_length: int, ):
-    prediction_range = PeriodRange.from_start_and_n_periods(
-        Month(historic_data.end_timestamp).to_string(), prediction_length)
-    climate_predictor = MonthlyClimatePredictor()
-    climate_predictor.train(historic_data)
+    delta = historic_data.period_range[0].time_delta
+    prediction_range = PeriodRange(historic_data.end_timestamp,
+                                   historic_data.end_timestamp + delta * prediction_length,
+                                   delta)
+
+    #prediction_range = PeriodRange.from_start_and_n_periods(
+    #    Month(historic_data.end_timestamp).to_string(), prediction_length)
+    #climate_predictor = MonthlyClimatePredictor()
+    #climate_predictor.train(historic_data)
+    climate_predictor= get_climate_predictor(historic_data)
     future_weather = climate_predictor.predict(prediction_range)
     predictions = predictor.predict(historic_data, future_weather)
     return predictions
diff --git a/climate_health/assessment/prediction_evaluator.py b/climate_health/assessment/prediction_evaluator.py
index e9dcc74f..64b9b46e 100644
--- a/climate_health/assessment/prediction_evaluator.py
+++ b/climate_health/assessment/prediction_evaluator.py
@@ -235,6 +235,7 @@ def plot_forecasts(predictors: list[Predictor], test_instance, truth, pdf_filena
 
 
 def plot_forecasts(predictor, test_instance, truth, pdf_filename):
+
     forecast_dict = _get_forecast_dict(predictor, test_instance)
     with PdfPages(pdf_filename) as pdf:
         for location, forecasts in forecast_dict.items():
@@ -243,7 +244,8 @@ def plot_forecasts(predictor, test_instance, truth, pdf_filename):
                 plt.figure(figsize=(8, 4))  # Set the figure size
                 t = _t[_t.index <= forecast.index[-1]]
                 forecast.plot(show_label=True)
-                plt.plot(t[-150:].to_timestamp())
+                plotting_context = 52*6
+                plt.plot(t[-plotting_context:].to_timestamp())
                 plt.title(location)
                 plt.legend()
                 pdf.savefig()
@@ -260,7 +262,8 @@ def plot_predictions(predictions: DataSet[Samples], truth: DataSet, pdf_filename
             plt.figure(figsize=(8, 4))  # Set the figure size
             # t = _t[_t.index <= prediction.index[-1]]
             prediction.plot(show_label=True)
-            plt.plot(t[-150:].to_timestamp())
+            context_length = 52*6
+            plt.plot(t[-context_length:].to_timestamp())
             plt.title(location)
             plt.legend()
             pdf.savefig()
diff --git a/climate_health/climate_predictor.py b/climate_health/climate_predictor.py
index b76f096b..804dcd75 100644
--- a/climate_health/climate_predictor.py
+++ b/climate_health/climate_predictor.py
@@ -6,9 +6,18 @@
 
 from .datatypes import ClimateData
 from climate_health.spatio_temporal_data.temporal_dataclass import DataSet
-from climate_health.time_period import PeriodRange
+from climate_health.time_period import PeriodRange, Month, Week
 
 
+def get_climate_predictor(train_data: DataSet[ClimateData]):
+    if isinstance(train_data.period_range[0], Month):
+        estimator = MonthlyClimatePredictor()
+    else:
+        assert isinstance(train_data.period_range[0], Week)
+        estimator = WeeklyClimatePredictor()
+    estimator.train(train_data)
+    return estimator
+
 
 class MonthlyClimatePredictor:
     def __init__(self):
@@ -16,7 +25,7 @@ def __init__(self):
         self._cls = None
 
     def _feature_matrix(self, time_period: PeriodRange):
-        return time_period.month[:,None] == np.arange(1, 13)
+        return time_period.month[:, None] == np.arange(1, 13)
 
     def train(self, train_data: DataSet[ClimateData]):
         train_data = train_data.remove_field('disease_cases')
@@ -35,10 +44,13 @@ def predict(self, time_period: PeriodRange):
         x = self._feature_matrix(time_period)
         prediction_dict = {}
         for location, models in self._models.items():
-            prediction_dict[location] = self._cls(time_period, **{field: model.predict(x).ravel() for field, model in models.items()})
+            prediction_dict[location] = self._cls(time_period, **{field: model.predict(x).ravel() for field, model in
+                                                                  models.items()})
         return DataSet(prediction_dict)
 
 
-
-
-
+class WeeklyClimatePredictor(MonthlyClimatePredictor):
+    def _feature_matrix(self, time_period: PeriodRange):
+        t = time_period.week[:, None] == np.arange(1, 53)
+        t[..., -1] |= time_period.week == 53
+        return t
diff --git a/climate_health/spatio_temporal_data/temporal_dataclass.py b/climate_health/spatio_temporal_data/temporal_dataclass.py
index 56de6126..dd228842 100644
--- a/climate_health/spatio_temporal_data/temporal_dataclass.py
+++ b/climate_health/spatio_temporal_data/temporal_dataclass.py
@@ -296,4 +296,7 @@ def from_fields(cls, dataclass: type[TimeSeriesData], fields: dict[str, 'DataSet
             new_dict[location] = dataclass(period_range, **{field: fields[field][location].fill_to_range(start_timestamp, end_timestamp).value for field in field_names})
         return cls(new_dict)
 
-
+    def plot(self):
+        for location, data in self.items():
+            df = data.to_pandas()
+            df.plot(x='time_period', title=location)
diff --git a/climate_health/time_period/__init__.py b/climate_health/time_period/__init__.py
index 0d216866..68900039 100644
--- a/climate_health/time_period/__init__.py
+++ b/climate_health/time_period/__init__.py
@@ -1,4 +1,4 @@
-from .date_util_wrapper import TimePeriod, Year, Month, Day, PeriodRange, delta_month, delta_week
+from .date_util_wrapper import TimePeriod, Year, Month, Day, PeriodRange, delta_month, delta_week, Week
 #from ._legacy_implementation import TimePeriod, Year, Month, Day
 from .period_range import period_range as get_period_range
 get_period_range = PeriodRange.from_time_periods
diff --git a/climate_health/time_period/date_util_wrapper.py b/climate_health/time_period/date_util_wrapper.py
index a229e386..0e7f4dad 100644
--- a/climate_health/time_period/date_util_wrapper.py
+++ b/climate_health/time_period/date_util_wrapper.py
@@ -2,12 +2,14 @@
 import logging
 from datetime import datetime
 from numbers import Number
-from typing import Union, Iterable
+from typing import Union, Iterable, Tuple
 
+import dateutil
 import numpy as np
 import pandas as pd
 from dateutil.parser import parse
 from dateutil.relativedelta import relativedelta
+from pytz import utc
 
 
 class DateUtilWrapper:
@@ -25,6 +27,10 @@ def __getattr__(self, item: str):
 class TimeStamp(DateUtilWrapper):
     _used_attributes = ('year', 'month', 'day', '__str__', '__repr__')
 
+    @property
+    def week(self):
+        return self._date.isocalendar()[1]
+
     def __init__(self, date: datetime):
         self._date = date
 
@@ -60,7 +66,7 @@ def __sub__(self, other: 'TimeStamp'):
         return TimeDelta(relativedelta(self._date, other._date))
 
     def _comparison(self, other: 'TimeStamp', func_name: str):
-        return getattr(self._date, func_name)(other._date)
+        return getattr(self._date.replace(tzinfo=utc), func_name)(other._date.replace(tzinfo=utc))
 
 
 class TimePeriod:
@@ -150,7 +156,7 @@ def time_delta(self) -> 'TimeDelta':
 
     @classmethod
     def parse(cls, text_repr: str):
-        if 'W' in text_repr:
+        if 'W' in text_repr or '/' in text_repr:
             return cls.parse_week(text_repr)
         try:
             year = int(text_repr)
@@ -172,9 +178,15 @@ def from_pandas(cls, period: pd.Period):
 
     @classmethod
     def parse_week(cls, week: str):
-        year, weeknr = week.split('W')
-        print('########', week)
-        return Week(int(year), int(weeknr))
+        if 'W' in week:
+            year, weeknr = week.split('W')
+            return Week(int(year), int(weeknr))
+        elif '/' in week:
+            start, end = week.split('/')
+            start_date = dateutil.parser.parse(start)
+            end_date = dateutil.parser.parse(end)
+            assert relativedelta(end_date, start_date).days == 6, f'Week must be 7 days {start_date} {end_date}'
+            return Week(start_date)  # type: ignore
 
     @property
     def start_timestamp(self):
@@ -206,10 +218,20 @@ def id(self):
         return self._date.strftime('%Y%m%d')
 
 
+class WeekNumbering:
+    @staticmethod
+    def get_week_info(date: datetime) -> Tuple[int, int, int]:
+        return date.isocalendar()
+
+    @staticmethod
+    def get_date(year: int, week: int, day: int) -> datetime:
+        return datetime.strptime(f'{year}-W{week}-{day}', "%G-W%V-%w")
+
 
 class Week(TimePeriod):
     _used_attributes = []#'year']
     _extension = relativedelta(weeks=1)
+    _week_numbering = WeekNumbering
 
     @property
     def id(self):
@@ -224,12 +246,15 @@ def __init__(self, date, *args, **kwargs):
             week_nr = args[0] if args else kwargs['week']
             self._date = self.__date_from_numbers(year, week_nr)
             self.week = week_nr
-            self.year = self._date.year
+            self.year = year
+            #self.year = self._date.year
         else:
             if isinstance(date, TimeStamp):
                 date = date._date
-            self.week = date.isocalendar()[1]
-            self.year = date.isocalendar()[0]
+            year, week, day = date.isocalendar()
+            self.week = week
+            self.year = year
+
             self._date = date
 
     def __sub__(self, other: 'TimePeriod'):
@@ -243,11 +268,18 @@ def __str__(self):
 
     __repr__ = __str__
 
-    def __date_from_numbers(cls, year: int, week_nr: int):
-        return datetime.strptime(f'{year}-W{week_nr}-1', "%Y-W%W-%w")
+    def __date_from_numbers(self, year: int, week_nr: int):
+        date = self._week_numbering.get_date(year, week_nr, 1)
+        #date = datetime.strptime(f'{year}-W{week_nr}-1', "%Y-W%W-%w")
+        assert date.isocalendar()[:2] == (year, week_nr), (date.isocalendar()[:2], year, week_nr)
+        return date
+
+    @classmethod
+    def _isocalendar_week_to_date(cls, year: int, week_nr: int, day: int):
+        return datetime.strptime(f'{year}-W{week_nr}-{day}', "%Y-W%V-%w")
 
     def topandas(self):
-        return self.__str__()
+        #return self.__str__()
         return pd.Period(self._date, freq='W-MON')
 
 
@@ -365,6 +397,10 @@ def month(self):
     def year(self):
         return np.array([p.start_timestamp.year for p in self])
 
+    @property
+    def week(self):
+        return np.array([p.start_timestamp.week for p in self])
+
     @property
     def delta(self):
         return self._time_delta
@@ -418,7 +454,8 @@ def _period_class(self):
         raise ValueError(f'Unknown time delta {self._time_delta}')
 
     def __iter__(self):
-        return (self._period_class((self._start_timestamp + self._time_delta * i)._date) for i in range(len(self)))
+        return (self._period_class((self._start_timestamp + self._time_delta * i)._date)
+                for i in range(len(self)))
 
     def __getitem__(self, item: slice | int):
         ''' Slice by numeric index in the period range'''
@@ -517,7 +554,10 @@ def from_ids(cls, ids: Iterable[str], fill_missing=False):
 
     @classmethod
     def from_start_and_n_periods(cls, start_period: pd.Period, n_periods: int):
-        period = TimePeriod.from_pandas(start_period)
+        if not isinstance(start_period, TimePeriod):
+            period = TimePeriod.from_pandas(start_period)
+        else:
+            period = start_period
         delta = period.time_delta
         return cls.from_time_periods(period, period + delta * (n_periods-1))
 
@@ -543,7 +583,8 @@ def searchsorted(self, period: TimePeriod, side='left'):
         if side not in ('left', 'right'):
             raise ValueError(f'Invalid side {side}')
         assert period.time_delta == self._time_delta, (period, self._time_delta)
-        n_steps = TimeDelta(relativedelta(period._date, self._start_timestamp._date)) // self._time_delta
+        n_steps = self._time_delta.n_periods(self._start_timestamp, period.start_timestamp)
+        # n_steps = TimeDelta(relativedelta(period._date, self._start_timestamp._date)) // self._time_delta
         if side == 'right':
             n_steps += 1
         n_steps = min(max(0, n_steps), len(self))  # if period is outside
diff --git a/pytest.ini b/pytest.ini
index e5ad5956..4f9797aa 100644
--- a/pytest.ini
+++ b/pytest.ini
@@ -1,6 +1,6 @@
 [pytest]
 #norecursedirs = tests/data_wrangling tests/external tests/spatio_temporal_data tests/
-norecursedirs = tests/data_wrangling tests/spatio_temporal_data tests/
+norecursedirs = tests/data_wrangling tests/spatio_temporal_data tests/ .mypy_cache
 ignore = ['tests/test_meteostat_wrapper']
 log_cli = True
 
diff --git a/scripts/clean_laos_data2.py b/scripts/clean_laos_data2.py
index 74bf5dab..5c2271be 100644
--- a/scripts/clean_laos_data2.py
+++ b/scripts/clean_laos_data2.py
@@ -2,6 +2,7 @@
 
 import numpy as np
 import pandas as pd
+from matplotlib import pyplot as plt
 
 from climate_health.datatypes import ClimateData, ClimateHealthTimeSeries, FullData, ClimateHealthData
 from climate_health.file_io.cleaners import laos_data
@@ -9,26 +10,69 @@
 from climate_health.time_period import TimePeriod
 
 filname = '/home/knut/Downloads/laodenguedata.csv'
+
+
 def parse_week(week):
     week, year = week.split()
     print(week, year)
     weekstr = string.Formatter().format_field(int(week[1:]), '02')
     return f'{year}W{weekstr}'
 
+
 raw_df = pd.read_csv(filname)
 #
 raw_df['Location'] = raw_df['Organisation unit']
 # Make a column for each unique value in the 'Data' column
 df = raw_df.pivot(index=['Period', 'Location'], columns='Data', values='Value')
 df = df.reset_index()
-df['Period']= [parse_week(week) for week in df.Period]
+df['Period'] = [parse_week(week) for week in df.Period]
 colnames = ['Climate-Rainfall', 'Climate-Temperature avg',
-       'NCLE: 7. Dengue cases (any)', 'Location', 'Period']
+            'NCLE: 7. Dengue cases (any)', 'Location', 'Period']
 true_colnames = ['rainfall', 'mean_temperature', 'disease_cases', 'location', 'time_period']
 df.rename(columns={colname: true_colname for colname, true_colname in zip(colnames, true_colnames)}, inplace=True)
 df = df.sort_values(by=['time_period', 'location'])
+
+
+def add_population_data(data):
+    laos_population = '''\
+        Vientiane Capital: ~820,000
+        Phongsali: ~177,000
+        Louangnamtha: ~176,000
+        Oudomxai: ~307,000
+        Bokeo: ~205,000
+        Louangphabang: ~431,000
+        Houaphan: ~294,000
+        Xainyabouli: ~381,000
+        Xiangkhouang: ~252,000
+        Vientiane: ~432,000
+        Bolikhamxai: ~275,000
+        Khammouan: ~415,000
+        Savannakhet: ~939,000
+        Salavan: ~396,000
+        Xekong: ~120,000
+        Champasak: ~694,000
+        Attapu: ~153,000
+        Xaisomboun: ~93,000'''
+    laos_population = {line.split(': ')[0].strip(): int(line.split(': ~')[1].replace(',', '')) for line in
+                       laos_population.split('\n')}
+    data_dict = {name[3:]: data for name, data in data.items()}
+    for name in data_dict.keys():
+        if name not in laos_population:
+            print(f'{name} not in population data', laos_population.keys())
+    full_data = {name: FullData(d.time_period, d.rainfall, d.mean_temperature, d.disease_cases,
+                                np.full(len(d), laos_population[name]))
+                 for name, d in data_dict.items()}
+    return DataSet(full_data)
+
+
 if __name__ == '__main__':
-    dataset = DataSet.from_pandas(df, dataclass=ClimateHealthData, fill_missing=True)
+    dataset = DataSet.from_pandas(
+        df,
+        dataclass=ClimateHealthData,
+        fill_missing=True)
+    dataset = add_population_data(dataset)
+    dataset.to_csv('/home/knut/Data/ch_data/weekly_laos_data.csv')
+
 
 
 if False:
@@ -68,32 +112,7 @@ def get_laos_climate(climate_filename):
     data = DataSet(full_dict)
     data.to_csv('/home/knut/Downloads/laos_data.csv')
 
-    laos_population = '''\
-    Vientiane Capital: ~820,000
-    Phongsali: ~177,000
-    Louangnamtha: ~176,000
-    Oudomxai: ~307,000
-    Bokeo: ~205,000
-    Louangphabang: ~431,000
-    Houaphan: ~294,000
-    Xainyabouli: ~381,000
-    Xiangkhouang: ~252,000
-    Vientiane: ~432,000
-    Bolikhamxai: ~275,000
-    Khammouan: ~415,000
-    Savannakhet: ~939,000
-    Salavan: ~396,000
-    Xekong: ~120,000
-    Champasak: ~694,000
-    Attapu: ~153,000
-    Xaisomboun: ~93,000'''
-    laos_population = {line.split(': ')[0]: int(line.split(': ~')[1].replace(',', '')) for line in
-                       laos_population.split('\n')}
-    data_dict = {name[3:]: data.data() for name, data in data.items()}
-    full_data = {name: FullData(d.time_period, d.rainfall, d.mean_temperature, d.disease_cases,
-                                np.full(len(d), laos_population[name]))
-                 for name, d in data_dict.items()}
     full_data = DataSet(full_data)
     full_data.to_csv('/home/knut/Data/laos_full_data.csv')
     # data = {name: FullData.combine(health.get_location(name).data(), spatio_temporal_dict.get_location(name).data(), laos_population[name])
-    #        for name in health.locations()}
\ No newline at end of file
+    #        for name in health.locations()}
diff --git a/scripts/evaluate_laos.py b/scripts/evaluate_laos.py
new file mode 100644
index 00000000..fd722947
--- /dev/null
+++ b/scripts/evaluate_laos.py
@@ -0,0 +1,12 @@
+from climate_health.assessment.prediction_evaluator import evaluate_model
+from climate_health.datatypes import FullData
+from climate_health.external.external_model import get_model_from_directory_or_github_url
+from climate_health.predictor.naive_estimator import NaiveEstimator
+from climate_health.spatio_temporal_data.temporal_dataclass import DataSet
+model_url = '/home/knut/Sources/chap_auto_ewars_weekly'
+#model_url = 'https://github.com/sandvelab/chap_auto_ewars'
+model = get_model_from_directory_or_github_url(model_url)
+# model = NaiveEstimator()
+dataset = DataSet.from_csv('/home/knut/Data/ch_data/weekly_laos_data.csv', FullData)
+if __name__ == '__main__':
+    evaluate_model(model, dataset, prediction_length=12, n_test_sets=41, report_filename='laos_weekly_report.pdf')
\ No newline at end of file
diff --git a/scripts/prediction_example.py b/scripts/prediction_example.py
index 024580dc..7af2f405 100644
--- a/scripts/prediction_example.py
+++ b/scripts/prediction_example.py
@@ -1,15 +1,24 @@
+import databricks.sdk.service.sql
+import numpy as np
+
 from climate_health.assessment.forecast import forecast_ahead, forecast_with_predicted_weather
 from climate_health.assessment.prediction_evaluator import plot_predictions
 from climate_health.data.datasets import ISIMIP_dengue_harmonized
+from climate_health.datatypes import FullData, HealthData
 from climate_health.external.external_model import get_model_from_directory_or_github_url
 from climate_health.external.r_models import models_path
+from climate_health.spatio_temporal_data.temporal_dataclass import DataSet
 
 if __name__ == '__main__':
-    model_name = 'https://github.com/sandvelab/chap_auto_ewars'
+    #model_name = 'https://github.com/sandvelab/chap_auto_ewars'
+    model_url = '/home/knut/Sources/chap_auto_ewars_weekly'
     #model_name = models_path / 'naive_python_model_with_mlproject_file'
-    estimator = get_model_from_directory_or_github_url(model_name)
-    dataset = ISIMIP_dengue_harmonized['vietnam']
+    estimator = get_model_from_directory_or_github_url(model_url)
+    #dataset = ISIMIP_dengue_harmonized['vietnam']
+    dataset = DataSet.from_csv('/home/knut/Data/ch_data/weekly_laos_data.csv', FullData)
     predictor = estimator.train(dataset)
-    predictions = forecast_with_predicted_weather(predictor, dataset, 3)
+    predictions = forecast_with_predicted_weather(predictor, dataset, 26)
     plot_predictions(predictions, dataset, 'prediction_example.pdf')
+    medians = DataSet({loc: HealthData(data.time_period, np.median(data.samples, axis=-1)) for loc, data in predictions.items()})
+    medians.to_csv('laos_weekly_predictions.csv')
 
diff --git a/tests/test_climate_predictor.py b/tests/test_climate_predictor.py
index fbaa645c..ff520367 100644
--- a/tests/test_climate_predictor.py
+++ b/tests/test_climate_predictor.py
@@ -1,10 +1,11 @@
 import numpy as np
 import pytest
 
-from climate_health.climate_predictor import MonthlyClimatePredictor
+from climate_health.climate_predictor import MonthlyClimatePredictor, WeeklyClimatePredictor
 from climate_health.datatypes import ClimateData
 from climate_health.spatio_temporal_data.temporal_dataclass import DataSet
-from climate_health.time_period import PeriodRange, Month
+from climate_health.time_period import PeriodRange, Month, Week
+
 
 
 @pytest.fixture
@@ -15,6 +16,14 @@ def climate_data():
         {'oslo': ClimateData(time_period, values, values * 2, values * 3),
          'stockholm': ClimateData(time_period, values, values * 2, values * 3)})
 
+@pytest.fixture
+def weekly_climate_data():
+    time_period = PeriodRange.from_time_periods(Week(2019, 1), Week(2020, 52))
+    values = np.arange(len(time_period))
+    return DataSet(
+        {'oslo': ClimateData(time_period, values, values * 2, values * 3),
+         'stockholm': ClimateData(time_period, values, values * 2, values * 3)})
+
 
 def test_climate_predictor(climate_data):
     predictor = MonthlyClimatePredictor()
@@ -22,4 +31,8 @@ def test_climate_predictor(climate_data):
     time_period = PeriodRange.from_time_periods(Month.parse('2021-01'), Month.parse('2021-12'))
     prediction = predictor.predict(time_period)
 
-
+def test_weekly_climate_predictor(weekly_climate_data):
+    predictor = WeeklyClimatePredictor()
+    predictor.train(weekly_climate_data)
+    time_period = PeriodRange.from_time_periods(Week(2021, 1), Week(2021, 52))
+    prediction = predictor.predict(time_period)
diff --git a/tests/test_forecast.py b/tests/test_forecast.py
index 5d1cc213..b117f51c 100644
--- a/tests/test_forecast.py
+++ b/tests/test_forecast.py
@@ -33,6 +33,13 @@ def test_multi_forecast():
 
 def test_forecast_ahead():
     model = NaiveEstimator()
-    dataset = dataset = ISIMIP_dengue_harmonized['vietnam']
+    dataset = ISIMIP_dengue_harmonized['vietnam']
+    prediction_length = 3
+    forecast_ahead(model, dataset, prediction_length)
+
+
+def test_forecast_with_predicted_weather():
+    model = NaiveEstimator()
+    dataset = ISIMIP_dengue_harmonized['vietnam']
     prediction_length = 3
     forecast_ahead(model, dataset, prediction_length)
diff --git a/tests/time_period/test_dateutil_wrapper.py b/tests/time_period/test_dateutil_wrapper.py
index 61417b98..301fac19 100644
--- a/tests/time_period/test_dateutil_wrapper.py
+++ b/tests/time_period/test_dateutil_wrapper.py
@@ -39,7 +39,7 @@ def test_init_week_with_numbers():
     week = Week(2023, 2)
     assert isinstance(week, Week)
     assert week.start_timestamp == TimeStamp.parse('2023-01-09')
-    assert week.topandas() == '2023W2'  # pd.Period('2023-01-09', freq='W-MON')
+    assert week.to_string() == '2023W2'  # pd.Period('2023-01-09', freq='W-MON')
 
 
 def test_parse(period1):