Upload New File

Sortieren/Exel.py

+# %% 
+import numpy as np
+import pandas as pd
+
+# %% 
+EMISSION_CSV = # Pfad zu co2_emission.csv
+GDP_CSV = # Pfad zu gdp.csv
+POP_TOTAL_CSV = # Pfad zu pop_toal.csv
+POP_GROW_CSV = # Pfad zu POP_GROW.csv
+AIR_CSV = # Pfad zu air.csv
+
+# %%
+FILTERED_EMISSION_CSV = # Pfad wo bereinigte Datei gespeichtert werden soll
+FILTERED_GDP_CSV = # Pfad wo bereinigte Datei gespeichtert werden soll
+FILTERED_POP_TOTAL_CSV = # Pfad wo bereinigte Datei gespeichtert werden soll
+FILTERED_POP_GROW_CSV = # Pfad wo bereinigte Datei gespeichtert werden soll
+FILTERED_AIR_CSV = # Pfad wo bereinigte Datei gespeichtert werden soll
+
+
+# %% 
+emission = np.array(pd.read_csv(filepath_or_buffer = EMISSION_CSV, header=None))
+gdp = np.array(pd.read_csv(filepath_or_buffer = GDP_CSV, header=None))
+pop_total = np.array(pd.read_csv(filepath_or_buffer = POP_TOTAL_CSV, header=None))
+pop_grow = np.array(pd.read_csv(filepath_or_buffer = POP_GROW_CSV, header=None))
+air = np.array(pd.read_csv(filepath_or_buffer = AIR_CSV, header=None))
+
+# %%
+""" Datenbereinigung: NaN wird entfernt"""
+import math
+def isnan(array):
+    idxs = []
+    x = array.shape[0]
+    for i in range(x):
+        if type(array[i]) == str:
+            continue
+        if math.isnan(float(array[i])):
+            idxs.append(i)
+    return idxs
+
+# %%
+""" Datenveränderung, population_growth """
+pop_grow = pop_grow.T
+greater2005 = np.argwhere(pop_grow[4:, 0] >= 2005) + 4
+lower2017 = np.argwhere(pop_grow[4:, 0] <= 2017) + 4 
+years = np.intersect1d(greater2005, lower2017)
+body = pop_grow[years]
+header = pop_grow[:4, :]
+""" Kreiere ID für CSV """
+id = np.zeros((1,265), dtype=object)
+x, y = id.shape
+for i in range(x):
+    for j in range(y):
+        id[i,j] = j
+id[0,0] = "id"
+header = np.concatenate((header, id), axis=0)
+""" Füge alles zusammen """
+filtered_pop_grow = np.concatenate((header, body), axis=0)
+np.savetxt(FILTERED_POP_GROW_CSV, filtered_pop_grow, delimiter=';', fmt='%s')
+# %%
+""" Datenveränderung, population_total """
+years = np.argwhere(pop_total[1:, 1].astype('float') >= 2005) + 1
+body = pop_total[years].reshape(2841, 3)
+header = pop_total[:1, :]
+""" Kreiere ID für CSV """
+id = np.zeros((2842,1), dtype=object)
+x, y = id.shape
+for i in range(x):
+    for j in range(y):
+        id[i,j] = i
+id[0,0] = "id"
+header = np.concatenate((id[:1], header), axis=1)
+body = np.concatenate((id[1:], body), axis=1)
+""" Füge alles zusammen """
+filtered_pop_total = np.concatenate((header, body), axis=0)
+np.savetxt(FILTERED_POP_TOTAL_CSV, filtered_pop_total, delimiter=';', fmt='%s')
+
+# %%
+""" Datenveränderung, population_gdp """
+gdp = gdp.T
+greater2005 = np.argwhere(gdp[4:, 0].astype('float') >= 2005) + 4
+lower2017 = np.argwhere(gdp[4:, 0].astype('float') <= 2017) + 4 
+years = np.intersect1d(greater2005, lower2017)
+body = gdp[years]
+header = gdp[:4, :]
+""" Kreiere ID für CSV """
+id = np.zeros((1,265), dtype=object)
+x, y = id.shape
+for i in range(x):
+    for j in range(y):
+        id[i,j] = j
+id[0,0] = "id"
+header = np.concatenate((header, id), axis=0)
+""" Füge alles zusammen """
+filtered_gdp = np.concatenate((header, body), axis=0)
+np.savetxt(FILTERED_GDP_CSV, filtered_gdp, delimiter=';', fmt='%s')
+
+# %%
+""" Datenveränderung, co2_emission """
+years = np.argwhere(emission[1:, 2].astype('float') >= 2005) + 1
+body = emission[years].reshape(2945,4)
+header = emission[:1, :]
+""" nan's finden und entfernen"""
+idx_nan = isnan(body[:, 1])
+body_without_nan = np.delete(body, idx_nan, axis=0)
+""" Kreiere ID für CSV """
+id = np.zeros((body_without_nan.shape[0]+1,1), dtype=object)
+x, y = id.shape
+for i in range(x):
+    for j in range(y):
+        id[i,j] = i
+id[0,0] = "id"
+header = np.concatenate((id[:1], header), axis=1)
+body = np.concatenate((id[1:], body_without_nan), axis=1)
+# """ Füge alles zusammen """
+filtered_emission = np.concatenate((header, body), axis=0)
+np.savetxt(FILTERED_EMISSION_CSV, filtered_emission, delimiter=';', fmt='%s')
+
+#%%
+""" Datenveränderung, air """
+greater2005 = np.argwhere(air[1:, 2].astype('float') >= 2005) + 1
+lower2017 = np.argwhere(air[1:, 2].astype('float') <= 2017) + 1
+years = np.intersect1d(greater2005, lower2017)
+body = air[years].reshape(3432,4)
+header = air[:1, :]
+""" Kreiere ID für CSV """
+id = np.zeros((3433,1), dtype=object)
+x, y = id.shape
+for i in range(x):
+    for j in range(y):
+        id[i,j] = i
+id[0,0] = "id"
+header = np.concatenate((id[:1], header), axis=1)
+body = np.concatenate((id[1:], body), axis=1)
+# """ Füge alles zusammen """
+filtered_air = np.concatenate((header, body), axis=0)
+np.savetxt(FILTERED_AIR_CSV, filtered_air, delimiter=';', fmt='%s')
+
+
+# %%
+
+# %%
+
+# %%