geocif 0.1.67__tar.gz → 0.1.68__tar.gz

{geocif-0.1.67/geocif.egg-info → geocif-0.1.68}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.67
+Version: 0.1.68
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.67 → geocif-0.1.68}/geocif/cei/definitions.py

@@ -1,11 +1,11 @@
 PHENOLOGICAL_STAGES = [1, 2, 3]
 dict_indices = {
     "GD4": ["Cold", "Growing degree days (sum of Tmean > 4 C)"],
-    #"CFD": ["Cold", "Maximum number of consecutive frost days (Tmin < 0 C)"],
-    #"FD": ["Cold", "Number of Frost Days (Tmin < 0C)"],
+    "CFD": ["Cold", "Maximum number of consecutive frost days (Tmin < 0 C)"],
+    "FD": ["Cold", "Number of Frost Days (Tmin < 0C)"],
     "HD17": ["Cold", "Heating degree days (sum of Tmean < 17 C)"],
-    #"ID": ["Cold", "Number of sharp Ice Days (Tmax < 0C)"],
-    #"CSDI": ["Cold", "Cold-spell duration index"],
+    "ID": ["Cold", "Number of sharp Ice Days (Tmax < 0C)"],
+    "CSDI": ["Cold", "Cold-spell duration index"],
     "TG10p": ["Cold", "Percentage of days when Tmean < 10th percentile"],
     "TN10p": ["Cold", "Percentage of days when Tmin < 10th percentile"],
     "TXn": ["Cold", "Minimum daily maximum temperature"],
@@ -70,10 +70,10 @@ dict_indices = {
         "Compound",
         "Days with TG > 75th percentile of daily mean temperature and RR >75th percentile of daily precipitation sum",
     ],
-    # "SD": ["Snow", "Mean of daily snow depth"],
-    # "SD1": ["Snow", "Number of days with snow depth >= 1 cm"],
-    # "SD5cm": ["Snow", "Number of days with snow depth >= 5 cm"],
-    # "SD50cm": ["Snow", "Number of days with snow depth >= 50 cm"],
+    "SD": ["Snow", "Mean of daily snow depth"],
+    "SD1": ["Snow", "Number of days with snow depth >= 1 cm"],
+    "SD5cm": ["Snow", "Number of days with snow depth >= 5 cm"],
+    "SD50cm": ["Snow", "Number of days with snow depth >= 50 cm"],
 }
 
 dict_ndvi = {

{geocif-0.1.67 → geocif-0.1.68}/geocif/geocif.py

@@ -598,15 +598,15 @@ class Geocif:
             df_region[f"Median {self.target}"].values, 3
         )
 
-        if f"Median {self.target} (2014-2018)" in df_region.columns:
-            df.loc[:, f"Median {self.target} (2014-2018)"] = np.around(
-                df_region[f"Median {self.target} (2014-2018)"].values, 3
-            )
-
-        if f"Median {self.target} (2013-2017)" in df_region.columns:
-            df.loc[:, f"Median {self.target} (2013-2017)"] = np.around(
-                df_region[f"Median {self.target} (2013-2017)"].values, 3
-            )
+        # if f"Median {self.target} (2014-2018)" in df_region.columns:
+        #     df.loc[:, f"Median {self.target} (2014-2018)"] = np.around(
+        #         df_region[f"Median {self.target} (2014-2018)"].values, 3
+        #     )
+        #
+        # if f"Median {self.target} (2013-2017)" in df_region.columns:
+        #     df.loc[:, f"Median {self.target} (2013-2017)"] = np.around(
+        #         df_region[f"Median {self.target} (2013-2017)"].values, 3
+        #     )
 
         if self.estimate_ci:
             if self.estimate_ci_for_all or self.forecast_season == self.today_year:
@@ -820,8 +820,8 @@ class Geocif:
                 + self.statistics_columns
                 + self.feature_names
                 + [f"Median {self.target}"]
-                + [f"Median {self.target} (2014-2018)"]
-                + [f"Median {self.target} (2013-2017)"]
+                #+ [f"Median {self.target} (2014-2018)"]
+                #+ [f"Median {self.target} (2013-2017)"]
                 + ["Region_ID"]
             )
             if self.check_yield_trend:
@@ -1011,13 +1011,13 @@ class Geocif:
             df, self.all_seasons_with_yield, self.number_median_years, self.target
         )
 
-        df = fe.compute_user_median_statistics(
-            df, [2014, 2015, 2016, 2017, 2018]
-        )
-
-        df = fe.compute_user_median_statistics(
-            df, [2013, 2014, 2015, 2016, 2017]
-        )
+        # df = fe.compute_user_median_statistics(
+        #     df, [2014, 2015, 2016, 2017, 2018]
+        # )
+        #
+        # df = fe.compute_user_median_statistics(
+        #     df, [2013, 2014, 2015, 2016, 2017]
+        # )
 
         if self.median_area_as_feature:
             df = fe.compute_median_statistics(
@@ -1393,6 +1393,9 @@ class Geocif:
             self.dg["ADM0_NAME"].str.lower().str.replace(" ", "_") == self.country
         ]
 
+        # Drop any duplicates based on Country Region column
+        self.dg_country = self.dg_country.drop_duplicates(subset=["Country Region"])
+
     def read_data(self, country, crop, season):
         """
 

{geocif-0.1.67 → geocif-0.1.68}/geocif/geocif_runner.py

@@ -26,41 +26,40 @@ def loop_execute(inputs):
     Returns:
 
     """
-    # from pycallgraph2 import Config, PyCallGraph, GlobbingFilter
-    # from pycallgraph2.output import GraphvizOutput
-    #
-    # graphviz = GraphvizOutput()
-    # graphviz.output_file = "geocif_visualization.png"
-    # plt.rcParams["figure.dpi"] = 600
-    # config = Config(max_depth=5)
-    # config.trace_filter = GlobbingFilter(
-    #     exclude=[
-    #         "pycallgraph.*",
-    #         "torch*",
-    #     ]
-    # )
-    #
-    # with PyCallGraph(output=graphviz, config=config):
-    project_name, country, crop, season, model, logger, parser, index = inputs
-
-    logger.info("=====================================================")
-    logger.info(f"\tStarting GEOCIF: {country} {crop} {season} {model}")
-    logger.info("=====================================================")
-
-    obj = geocif.Geocif(logger=logger,
-                        parser=parser,
-                        project_name=project_name)
-    obj.read_data(country, crop, season)
-
-    # Store config file in database, only execute this for
-    # the first iteration of the loop
-    if index == 0:
-        output.config_to_db(obj.db_path, obj.parser, obj.today)
-
-    # Setup metadata and run ML code
-    obj.setup(season, model)
-    if obj.simulation_stages:
-        obj.execute()
+    from pycallgraph2 import Config, PyCallGraph, GlobbingFilter
+    from pycallgraph2.output import GraphvizOutput
+
+    graphviz = GraphvizOutput()
+    graphviz.output_file = "geocif_visualization.png"
+    plt.rcParams["figure.dpi"] = 600
+    config = Config(max_depth=5)
+    config.trace_filter = GlobbingFilter(
+        exclude=[
+            "pycallgraph.*",
+        ]
+    )
+
+    with PyCallGraph(output=graphviz, config=config):
+        project_name, country, crop, season, model, logger, parser, index = inputs
+
+        logger.info("=====================================================")
+        logger.info(f"\tStarting GEOCIF: {country} {crop} {season} {model}")
+        logger.info("=====================================================")
+
+        obj = geocif.Geocif(logger=logger,
+                            parser=parser,
+                            project_name=project_name)
+        obj.read_data(country, crop, season)
+
+        # Store config file in database, only execute this for
+        # the first iteration of the loop
+        if index == 0:
+            output.config_to_db(obj.db_path, obj.parser, obj.today)
+
+        # Setup metadata and run ML code
+        obj.setup(season, model)
+        if obj.simulation_stages:
+            obj.execute()
 
 
 def gather_inputs(parser):

{geocif-0.1.67 → geocif-0.1.68}/geocif/ml/feature_selection.py

@@ -188,10 +188,24 @@ def select_features(X, y, method="RFE", min_features_to_select=3, threshold_nan=
 
         # Get the selected feature names
         selected_features = X.columns[selected_features].tolist()
+    elif method == "lasso":
+        from sklearn.linear_model import LassoLarsCV
+        from sklearn.feature_selection import SelectFromModel
+
+        # Fit Lasso model (L1 regularization) to perform feature selection
+        lasso = LassoLarsCV(cv=5)
+        lasso.fit(X, y)
+
+        # Use SelectFromModel to remove features with zero coefficients
+        selector = SelectFromModel(lasso, prefit=True)
+
+        # Get the selected features
+        selected_features = X.columns[selector.get_support()].tolist()
+        print(selected_features)
     elif method == "BorutaPy":
         from boruta import BorutaPy
 
-        selector = BorutaPy(forest, n_estimators="auto", random_state=42)
+        selector = BorutaPy(forest, n_estimators="auto", random_state=42, verbose=0)
         selector.fit(X.values, y.values)
         selected_features_mask = selector.support_
         selected_features = X.columns[selected_features_mask].tolist()

{geocif-0.1.67 → geocif-0.1.68}/geocif/ml/stats.py

@@ -203,7 +203,7 @@ def add_statistics(
         fn = "illinois.csv"
     elif country == "Ethiopia":
         # HACK
-        fn = "ethiopia_wheat_summary_formatted.csv"
+        fn = "adm_crop_production.csv"
     else:
         fn = "adm_crop_production.csv"
     df_fewsnet = pd.read_csv(dir_stats / fn, low_memory=False)

{geocif-0.1.67 → geocif-0.1.68}/geocif/viz/tmp.py

@@ -1,6 +1,4 @@
 import geopandas as gpd
-import pandas as pd
-import matplotlib.pyplot as plt
 import palettable as pal
 import matplotlib.colors as mcolors
 
@@ -9,7 +7,7 @@ import glob
 import os
 
 # 1. Specify the directory containing your .dta files:
-data_dir = r"C:\Users\ritvik\Downloads\maize_yield\maize_yield"
+data_dir = r"."
 
 # 2. Use glob to find all .dta files in that directory:
 dta_files = glob.glob(os.path.join(data_dir, "*.dta"))
@@ -20,6 +18,13 @@ dataframes = [pd.read_stata(f) for f in dta_files]
 # 4. Concatenate them all into one DataFrame (row-wise):
 merged_df = pd.concat(dataframes, ignore_index=True)
 
+# Replace null values in PROD98CQ with those in PROD columns
+merged_df['PROD98CQ'] = merged_df['PROD98CQ'].fillna(merged_df['PROD'])
+merged_df['YEAR'] = merged_df['YEAR'].fillna(merged_df['year'])
+
+# Drop rows where AREAH is 0
+merged_df = merged_df[merged_df['AREAH'] != 0]
+
 merged_df['ZONE'] = merged_df['ZONE'].astype(int)
 merged_df['DIST'] = merged_df['DIST'].astype(int)
 
@@ -36,7 +41,7 @@ merged_df['W_CODE'] = '7' + merged_df['W_CODE']
 merged_df['W_CODE'] = merged_df['W_CODE'].str.replace('.0', '')
 merged_df['W_CODE'] = merged_df['W_CODE'].astype(int)
 
-dg = gpd.read_file(r"D:\Users\ritvik\projects\GEOGLAM\Input\countries\wolayita\wolayita_dissolved.shp")
+dg = gpd.read_file(r"wolayita_dissolved.shp")
 dg = dg[['W_CODE', 'W_NAME']]
 
 # Merge the two dataframes on W_CODE
@@ -48,8 +53,8 @@ merged_df = merged_df.dropna(subset=['PROD98CQ', 'AREAH'])
 # Compte yield column
 merged_df['yield'] = merged_df['PROD98CQ'] / merged_df['AREAH']
 
-# create a new dataframe which computes average yield by W_NAME for each year
-df_avg_yield = merged_df.groupby(['W_NAME', 'YEAR'])['yield'].mean().reset_index()
+# create a new dataframe which computes average yield by W_NAME for each year, do a weighted average using FWEIGHT column
+df_avg_yield = merged_df.groupby(['W_NAME', 'YEAR']).apply(lambda x: np.average(x['yield'], weights=x['FWEIGHT'])).reset_index(name='yield')
 
 # Change W_NAME column to title case
 df_avg_yield['W_NAME'] = df_avg_yield['W_NAME'].str.title()
@@ -64,7 +69,15 @@ df_avg_yield = df_avg_yield.pivot(index='W_NAME', columns='YEAR', values='yield'
 df_avg_yield.index.name = None
 df_avg_yield.columns.name = None
 
-df_avg_yield.to_csv('wolayita_yields.csv')
+df_avg_yield.to_csv('wolayita_yields_v8.csv')
+breakpoint()
+# Compare wolayita_yields_v2.csv with wolayita_yields.csv
+# 1. Load the two CSV files
+df_v1 = pd.read_csv('wolayita_yields.csv')
+df_v2 = pd.read_csv('wolayita_yields_v2.csv')
+
+# 2. Check if the two DataFrames are equal
+print(df_v1.equals(df_v2))
 
 breakpoint()
 # 5. (Optional) Inspect the merged DataFrame

{geocif-0.1.67 → geocif-0.1.68/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.67
+Version: 0.1.68
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.67 → geocif-0.1.68}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.67",
+    version="0.1.68",
     zip_safe=False,
 )