aa

project/analysis.py

@@ -1,6 +1,13 @@
 import os
 from sqlalchemy import create_engine, inspect
 import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import statsmodels.api as sm
+
+
 
 
 script_dir = os.path.dirname(__file__)
@@ -39,6 +46,8 @@ def count_events(year):
     return ((df_bau['startDate'].dt.year <= year) & (df_bau['endDate'].dt.year >= year)).sum()
 
 years_df['Event_Count'] = years_df['Year'].apply(count_events)
+years_df = years_df.rename(columns={'Event_Count': 'Baustellen'})
+
 
 years_df = years_df.merge(df_eis[['Year', 'Beförderte Güter']], on='Year', how='left')
 years_df = years_df.rename(columns={'Beförderte Güter': 'Beförderte Güter Eisenbahn'})
@@ -49,3 +58,59 @@ def count_events(year):
 
 years_df.to_sql(name="baustellen_per_year", con=engine, if_exists="replace", index=False)
 
+
+
+years_df['Change in Eisenbahn per Event'] = years_df['Beförderte Güter Eisenbahn'].pct_change() / years_df['Baustellen'].pct_change()
+years_df['Change in Straße per Event'] = years_df['Beförderte Güter Straße'].pct_change() / years_df['Baustellen'].pct_change()
+
+# Filtering out the first row as percentage change is not defined for the first entry
+years_df = years_df.iloc[1:]
+years_df = years_df.loc[years_df['Year'] < 2023]
+
+print(years_df.head(20))
+
+# Plotting
+plt.figure(figsize=(12, 6))
+plt.plot(years_df['Year'], years_df['Beförderte Güter Eisenbahn'], label='Shipment on rails in kTons', marker='o')
+plt.plot(years_df['Year'], years_df['Beförderte Güter Straße'], label='Shipment on road in kTons', marker='x')
+plt.title('Goods Transported on rail and road in kTons')
+plt.xlabel('Year')
+plt.ylabel('Weight in kTons')
+plt.legend()
+plt.grid(True)
+plt.show()
+
+
+#regression analysis on trains 
+X = years_df[['Baustellen']]
+y = years_df['Beförderte Güter Eisenbahn']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
+model = LinearRegression()
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+mse = mean_squared_error(y_test, y_pred)
+print(f"Mean Squared Error: {mse}")
+print(f"Coefficients: {model.coef_}")
+print(f"Intercept: {model.intercept_}")
+
+X = sm.add_constant(X)
+model = sm.OLS(y, X)
+results = model.fit()
+print(results.summary())
+
+#regression analysis on streets 
+X = years_df[['Baustellen']]
+y = years_df['Beförderte Güter Straße']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
+model = LinearRegression()
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+mse = mean_squared_error(y_test, y_pred)
+print(f"Mean Squared Error: {mse}")
+print(f"Coefficients: {model.coef_}")
+print(f"Intercept: {model.intercept_}")
+
+X = sm.add_constant(X)
+model = sm.OLS(y, X)
+results = model.fit()
+print(results.summary())

project/requirements.txt

@@ -11,3 +11,6 @@ six==1.16.0
 SQLAlchemy==1.4.46
 typing_extensions==4.5.0
 geopandas
+matplotlib
+sklearn
+statsmodels