added first lecture

.gitignore

+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser

.idea/.gitignore

+# Default ignored files
+/workspace.xml
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Pipenv (predictive-analytics)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/predictive-analytics.iml" filepath="$PROJECT_DIR$/.idea/predictive-analytics.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/predictive-analytics.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TestRunnerService">
+    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

Pipfile

+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[dev-packages]
+
+[packages]
+numpy = "*"
+matplotlib = "*"
+pandas = "*"
+scikit-learn = "*"
+keras = "*"
+tensorflow = "*"
+statsmodels = "*"
+xlrd = "*"
+
+[requires]
+python_version = "3.7"

res/airline_passengers.csv

+Month;Passengers
+1949-01;224
+1949-02;236
+1949-03;264
+1949-04;258
+1949-05;242
+1949-06;270
+1949-07;296
+1949-08;296
+1949-09;272
+1949-10;238
+1949-11;208
+1949-12;236
+1950-01;230
+1950-02;252
+1950-03;282
+1950-04;270
+1950-05;250
+1950-06;298
+1950-07;340
+1950-08;340
+1950-09;316
+1950-10;266
+1950-11;228
+1950-12;280
+1951-01;290
+1951-02;300
+1951-03;356
+1951-04;326
+1951-05;344
+1951-06;356
+1951-07;398
+1951-08;398
+1951-09;368
+1951-10;324
+1951-11;292
+1951-12;332
+1952-01;342
+1952-02;360
+1952-03;386
+1952-04;362
+1952-05;366
+1952-06;436
+1952-07;460
+1952-08;484
+1952-09;418
+1952-10;382
+1952-11;344
+1952-12;388
+1953-01;392
+1953-02;392
+1953-03;472
+1953-04;470
+1953-05;458
+1953-06;486
+1953-07;528
+1953-08;544
+1953-09;474
+1953-10;422
+1953-11;360
+1953-12;402
+1954-01;408
+1954-02;376
+1954-03;470
+1954-04;454
+1954-05;468
+1954-06;528
+1954-07;604
+1954-08;586
+1954-09;518
+1954-10;458
+1954-11;406
+1954-12;458
+1955-01;484
+1955-02;466
+1955-03;534
+1955-04;538
+1955-05;540
+1955-06;630
+1955-07;728
+1955-08;694
+1955-09;624
+1955-10;548
+1955-11;474
+1955-12;556
+1956-01;568
+1956-02;554
+1956-03;634
+1956-04;626
+1956-05;636
+1956-06;748
+1956-07;826
+1956-08;810
+1956-09;710
+1956-10;612
+1956-11;542
+1956-12;612
+1957-01;630
+1957-02;602
+1957-03;712
+1957-04;696
+1957-05;710
+1957-06;844
+1957-07;930
+1957-08;934
+1957-09;808
+1957-10;694
+1957-11;610
+1957-12;672
+1958-01;680
+1958-02;636
+1958-03;724
+1958-04;696
+1958-05;726
+1958-06;870
+1958-07;982
+1958-08;1010
+1958-09;808
+1958-10;718
+1958-11;620
+1958-12;674
+1959-01;720
+1959-02;684
+1959-03;812
+1959-04;792
+1959-05;840
+1959-06;944
+1959-07;1096
+1959-08;1118
+1959-09;926
+1959-10;814
+1959-11;724
+1959-12;810
+1960-01;834
+1960-02;782
+1960-03;838
+1960-04;922
+1960-05;944
+1960-06;1070
+1960-07;1244
+1960-08;1212
+1960-09;1016
+1960-10;922
+1960-11;780
+1960-12;864
\ No newline at end of file

src/airline-lstm/main.py

+import math
+
+import numpy
+import matplotlib.pyplot as plt
+import pandas as pd
+import math
+from keras.models import Sequential
+from keras.layers import Dense, LSTM
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.metrics import mean_squared_error
+
+if __name__ == '__main__':
+    print('Hi')

src/airline-passengers/main.py

+import math
+
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+from pandas.plotting import register_matplotlib_converters, lag_plot, autocorrelation_plot
+from statsmodels.graphics.tsaplots import plot_acf
+from statsmodels.tsa.arima_model import ARIMA
+
+register_matplotlib_converters()
+
+
+class AirlinePassengers:
+    def __init__(self, file_path: str):
+        self.df = pd.read_excel(file_path)
+        self.df['Month'] = pd.to_datetime(self.df['Month'])
+
+        self.time = self.df['Month']
+        self.passengers = self.df['Passengers']
+
+    def plot_initial(self):
+        plt.plot(self.time, self.passengers, label='Initial')
+        plt.title('Passengers per Month')
+        plt.xlabel('Time')
+        plt.ylabel('Passengers')
+        plt.legend()
+
+        plt.show()
+
+    def plot_moving_average_without_pandas(self, windows=None):
+        if windows is None:
+            windows = [3]
+
+        for window in windows:
+            moving_averages = []
+            start = math.floor(window / 2)
+            end = len(self.passengers) - start
+
+            for i in range(end):
+                if i >= start:
+                    value = 0
+                    for j in range(i - start, i + start + 1):
+                        value = value + self.passengers[j]
+                    value = value / window
+                    moving_averages.append(value)
+                else:
+                    moving_averages.append(np.nan)
+
+            for i in range(start):
+                moving_averages.append(np.nan)
+
+            plt.plot(self.time, moving_averages, label=f'Window={window}')
+
+        plt.plot(self.time, self.passengers, label='Initial')
+
+        plt.title('Initial plot vs moving averages')
+        plt.xlabel('Time')
+        plt.ylabel('Passengers')
+
+        plt.legend()
+        plt.show()
+
+    def plot_exponential_average_without_pandas(self, alpha=0.3):
+        exponential_averages = []
+
+        for i in range(len(self.passengers)):
+            if i == 0:
+                exponential_averages.append(self.passengers[i])
+            else:
+                exponential_averages.append(alpha * self.passengers[i] + (1 - alpha) * exponential_averages[i - 1])
+
+        plt.plot(self.time, self.passengers, label='Initial')
+        plt.plot(self.time, exponential_averages, label=f'Alpha={alpha}')
+
+        plt.title('Initial plot vs exponential averages')
+        plt.xlabel('Time')
+        plt.ylabel('Passengers')
+        plt.legend()
+
+        plt.show()
+
+    def plot_moving_averages_with_pandas(self, windows=None):
+        if windows is None:
+            windows = [3]
+
+        for window in windows:
+            rolling_mean = self.df.rolling(window=window).mean()
+            plt.plot(self.time, rolling_mean, label=f'Window={window}')
+
+        plt.plot(self.time, self.passengers, label='Initial')
+
+        plt.title('Initial vs rolling mean pandas')
+        plt.xlabel('Time')
+        plt.ylabel('Passengers')
+
+        plt.legend()
+        plt.show()
+
+    def plot_auto_correlation_hyndman_without_pandas(self, lags=140):
+        mean = np.mean(self.passengers)
+        variance = np.var(self.passengers)
+
+        acf = []
+        end = lags - 1
+
+        for tau in range(end):
+            sum_covariance = 0
+            for i in range(tau + 1, len(self.passengers)):
+                sum_covariance += (self.passengers[i] - mean) * (self.passengers[i - tau] - mean)
+            acf.append(sum_covariance / (variance * (len(self.passengers) - 1)))
+
+        plt.stem(acf, use_line_collection=True)
+        plt.show()
+
+    def plot_adjacent_values(self):
+        lag_plot(self.passengers, lag=1, label='Passengers')
+
+        plt.title('Compare adjacent values')
+        plt.legend()
+
+        plt.show()
+
+    def plot_auto_correlation_with_pandas(self):
+        data_frame = pd.concat([self.passengers.shift(1), self.passengers], axis=1, names=['t-1, t+1'])
+
+        print(f'Correlation: {data_frame.corr()}')
+
+        autocorrelation_plot(self.passengers)
+
+        plt.show()
+
+    def plot_auto_correlation_with_stats_models(self, lags=140):
+        plot_acf(self.passengers, lags=lags)
+
+        plt.show()
+
+    def plot_naive_forecast(self):
+        forecast = [math.nan]
+
+        for value in self.passengers:
+            forecast.append(value)
+
+        del forecast[-1]
+
+        me = 0
+        mae = 0
+        mse = 0
+
+        for value, forecast_value in zip(self.passengers, forecast):
+            if not math.isnan(forecast_value):
+                diff = value - forecast_value
+
+                me += diff
+                mae += np.abs(diff)
+                mse += diff * diff
+
+        me /= len(forecast)
+        mae /= len(forecast)
+        mse /= len(forecast)
+
+        print(f"Mean Error: {me}")
+        print(f"Mean Absolute Error: {mae}")
+        print(f"Mean Square Error: {mse}")
+
+        plt.plot(self.time, self.passengers, label='Initial data')
+        plt.plot(self.time, forecast, label='Naive forecast')
+
+        plt.title('Naive forecast')
+        plt.xlabel('Time')
+        plt.ylabel('Passengers')
+        plt.legend()
+
+        plt.show()
+
+    def plot_arima_model(self):
+        results = ARIMA(self.passengers, order=(2, 1, 2)).fit(disp=-1)
+
+        predictions = results.fittedvalues.cumsum()
+
+        # [1:] ignores the value at index 0, because fittedvalues and predictions are 1 indexed
+        plt.plot(self.time, self.passengers, label='Initial data')
+        plt.plot(self.time[1:], results.fittedvalues, label='estimated differences')
+        plt.plot(self.time[1:], predictions, label='accumulated sum')
+
+        plt.title('ARIMA model output')
+        plt.xlabel('Time')
+        plt.ylabel('Passengers')
+        plt.legend()
+
+        plt.show()
+
+    def plot_arima_forecast(self):
+        results = ARIMA(self.passengers, order=(2, 1, 2)).fit(disp=-1)
+
+        results.plot_predict(1, 264)
+        plt.show()
+
+
+if __name__ == '__main__':
+    data_set = AirlinePassengers('../../res/airline-passengers.xls')
+
+    data_set.plot_initial()
+    data_set.plot_moving_average_without_pandas([3, 7, 11, 27])
+    data_set.plot_exponential_average_without_pandas()
+    data_set.plot_moving_averages_with_pandas([3, 7, 11, 27])
+    data_set.plot_auto_correlation_hyndman_without_pandas()
+    data_set.plot_adjacent_values()
+    data_set.plot_auto_correlation_with_stats_models()
+    data_set.plot_naive_forecast()
+    data_set.plot_arima_model()
+    data_set.plot_arima_forecast()