zadanie 5

Dockerfile

@@ -7,13 +7,17 @@ RUN apt install -y git
 RUN apt install -y python3-pip
 RUN pip3 install --user kaggle
 RUN pip3 install --user pandas
+RUN pip3 install --user numpy
 RUN pip3 install --user seaborn
 RUN pip3 install --user sklearn
 RUN pip3 install --user matplotlib
+RUN pip3 install --user tensorflow
 
 WORKDIR /app
 
 COPY ./skrypt.sh ./
 COPY ./zadanie2.py ./
+COPY ./zadanie5.py ./
 
-CMD ./zadanie2.py
+CMD ./zadanie2.py
+CMD ./zadanie5.py

dataset_stats/Jenkinsfile

@@ -1,6 +1,6 @@
 pipeline {
     agent {
-        docker { image 'shroomy/ium:1' }
+        docker { image 'shroomy/ium:2' }
     }
     parameters {
         buildSelector(defaultSelector: 
@@ -31,4 +31,4 @@ pipeline {
         }
     }
 
-}
+}

zadanie5.py

@@ -0,0 +1,51 @@
+#! /usr/bin/python3
+from tensorflow.keras.models import Sequential, load_model
+from tensorflow.keras.layers import Dense
+from sklearn.metrics import accuracy_score, classification_report
+import pandas as pd
+from sklearn.model_selection import train_test_split
+import numpy as np
+import requests
+url = 'https://git.wmi.amu.edu.pl/s434695/ium_434695/raw/commit/2301fb86e434734376f73503307a8f3255a75cc6/vgsales.csv'
+r = requests.get(url, allow_redirects=True)
+
+open('vgsales.csv', 'wb').write(r.content)
+df = pd.read_csv('vgsales.csv')
+
+
+
+def regression_model():
+    model = Sequential()
+    model.add(Dense(32,activation = "relu", input_shape = (x_train.shape[1],)))
+    model.add(Dense(64,activation = "relu"))
+    model.add(Dense(1,activation = "relu"))
+    
+    model.compile(optimizer = "adam", loss = "mean_squared_error")
+    return model
+
+df['Nintendo'] = df['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+df = df.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
+df
+
+y = df.Nintendo
+
+df=((df-df.min())/(df.max()-df.min()))
+
+x = df.drop(['Nintendo'],axis = 1)
+
+x_train, x_test, y_train, y_test = train_test_split(x,y , test_size=0.2,train_size=0.8, random_state=21)
+
+model = regression_model()
+model.fit(x_train, y_train, epochs = 600, verbose = 1)
+
+y_pred = model.predict(x_test)
+
+y_pred[:5]
+
+y_pred = np.around(y_pred, decimals=0)
+
+y_pred[:5]
+
+print(accuracy_score(y_test, y_pred))
+
+print(classification_report(y_test,y_pred))