Upload recomender_system_cluster_based.py

recomender_system_cluster_based.py

@@ -0,0 +1,301 @@
+# -*- coding: utf-8 -*-
+"""recomender2.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1WTIRumzmdqNSB2Z2dIv3r2LkSN5CdoU5
+"""
+
+from google.colab import drive
+drive.mount('/content/drive')
+
+import os
+os.environ['KAGGLE_CONFIG_DIR'] = "/content/drive/MyDrive/kaggle"
+
+# Commented out IPython magic to ensure Python compatibility.
+# %ls
+
+import pandas as pd
+import numpy as np
+from matplotlib import pyplot as plt
+from sklearn.cluster import KMeans
+from sklearn.metrics import silhouette_score
+from sklearn.preprocessing import scale, StandardScaler, normalize
+from yellowbrick.cluster import KElbowVisualizer
+from sklearn.manifold import TSNE
+import seaborn as sns
+import random
+
+df1=pd.read_csv('/content/drive/MyDrive/kaggle/ratings.csv')
+df2=pd.read_csv('/content/drive/MyDrive/kaggle/movies_metadata.csv')
+df3=pd.read_csv('/content/drive/MyDrive/kaggle/ratings_small.csv')
+
+df2
+
+df2.shape
+
+df2.columns
+
+df2.info()
+
+df2.isna().sum()
+
+data=df2[['revenue','runtime','vote_average','vote_count','title']]
+
+data
+
+data=data.fillna(0)
+
+#scale the data
+
+scaler = StandardScaler()
+data_scaled = scaler.fit_transform(data.iloc[:, :-1])
+data_scaled
+
+inertia = []
+silhouette_scores = []
+k_values = range(2, 10)
+for k in k_values:
+    kmeans = KMeans(n_clusters=k, random_state=3,n_init=4)
+    kmeans.fit(data_scaled)
+    #center=kmeans.cluster_centers
+    inertia.append(kmeans.inertia_)
+    silhouette_scores.append(silhouette_score(data_scaled, kmeans.labels_))
+    print(silhouette_scores)
+
+plt.figure(figsize=(12, 4))
+plt.subplot(1, 2, 1)
+plt.plot(k_values, inertia, marker='o')
+plt.xlabel('Number of clusters (k)')
+plt.ylabel('Inertia')
+plt.title('Inertia vs. Number of Clusters')
+
+plt.subplot(1, 2, 2)
+plt.plot(k_values, silhouette_scores, marker='o')
+plt.xlabel('Number of clusters (k)')
+plt.ylabel('Silhouette Score')
+plt.title('Silhouette Score vs. Number of Clusters')
+
+plt.tight_layout()
+plt.show()
+
+model = KMeans(n_init=8)
+visualiser = KElbowVisualizer(model, k=(2,12))
+visualiser.fit(data_scaled)
+visualiser.show()
+
+kmeans_mod = KMeans(n_clusters=5, n_init=10)
+kmeans_mod.fit(data_scaled)
+
+labels =kmeans_mod.fit_predict(data_scaled)
+data['cluster']=labels
+data=data[['revenue','runtime','vote_average','vote_count','cluster','title']]
+data
+
+data['cluster'].value_counts()
+
+tsne = TSNE(n_components=2, random_state=42)
+X_tsne = tsne.fit_transform(data_scaled)
+
+plt.figure(figsize=(8,6))
+plt.scatter(X_tsne[:, 0], X_tsne[:, 1], c=kmeans.labels_, cmap='viridis')
+plt.xlabel('t-SNE Dimension 1')
+plt.ylabel('t-SNE Dimension 2')
+plt.title('Clustering Results with K-Means (k=5)'.format(5))
+plt.colorbar(label='Cluster')
+plt.show()
+
+cdata=data[['cluster','title']]
+cdata
+
+cluster0=[]
+cluster1=[]
+cluster2=[]
+cluster3=[]
+cluster4=[]
+
+filmname=''
+for i in cdata.iloc():
+     if i[0]==0:
+      filmname=''
+      filmname=i[1]
+      #print(filmname)
+      cluster0.append(filmname)
+     elif i[0]==1:
+        filmname=''
+        filmname=i[1]
+        cluster1.append(filmname)
+     elif i[0]==2:
+        filmname=''
+        filmname=i[1]
+        cluster2.append(filmname)
+     if i[0]==3:
+        filmname=''
+        filmname=i[1]
+        cluster3.append(filmname)
+     if i[0]==4:
+        filmname=''
+        filmname=i[1]
+        cluster4.append(filmname)
+print(len(cluster0))
+print(len(cluster1))
+print(len(cluster2))
+print(len(cluster3))
+print(len(cluster4))
+
+
+print((cluster0))
+print((cluster1))
+print((cluster2))
+print((cluster3))
+print((cluster4))
+
+data=data.iloc[:, :-1]
+data
+
+from sklearn.decomposition import PCA
+pca_mod = PCA(n_components=3)
+# fit the PCA model to the (scaled) features
+pca_mod.fit(data)
+
+# plot the cumulative variance explained across all the components
+# start the explained variance at 0
+exp_variance = np.insert(pca_mod.explained_variance_ratio_, 0, 0)
+
+# plot the explained variance
+figure = plt.figure(figsize=(8, 5))
+
+plt.plot(np.cumsum(exp_variance))
+plt.xticks(range(0,6))
+plt.xlabel("Number of principal components (PCs)", size=13)
+plt.ylabel("% cumulative variance explained", size=13)
+plt.title("Cumulative variance explained", size=15)
+
+plt.show()
+np.cumsum(exp_variance)
+
+pca_mod = PCA(n_components=3)
+
+data_pca = pd.DataFrame(data=pca_mod.fit_transform(data_scaled),
+                        columns=['PC1', 'PC2', 'PC3'])
+
+# view data frame of PCs
+data_pca.head()
+
+# combine data for plotting
+data.reset_index(drop=True, inplace=True)
+data_pca.reset_index(drop=True, inplace=True)
+plot_data = pd.concat([data_pca, data['cluster']], axis=1)
+
+# visualise the clusters by plotting the PCAs in a scatter/pair plot,
+# with points colored by cluster membership
+sns.pairplot(data=plot_data,
+             hue='cluster',
+             palette='Set1',
+             corner=True)
+
+cluster=[cluster0,cluster1,cluster2,cluster3,cluster4]
+
+def recomender(input1,input2,input3):
+
+  encod_input1=[]
+  encod_input2=[]
+  encod_input3=[]
+
+
+  encod_input1.append(cluster0.count(input1))
+  encod_input1.append(cluster1.count(input1))
+  encod_input1.append(cluster2.count(input1))
+  encod_input1.append(cluster3.count(input1))
+  encod_input1.append(cluster4.count(input1))
+
+
+
+  encod_input2.append(cluster0.count(input2))
+  encod_input2.append(cluster1.count(input2))
+  encod_input2.append(cluster2.count(input2))
+  encod_input2.append(cluster3.count(input2))
+  encod_input2.append(cluster4.count(input2))
+
+
+
+  encod_input3.append(cluster0.count(input3))
+  encod_input3.append(cluster1.count(input3))
+  encod_input3.append(cluster2.count(input3))
+  encod_input3.append(cluster3.count(input3))
+  encod_input3.append(cluster4.count(input3))
+
+
+  return encod_input1,encod_input2,encod_input3
+
+
+def recomender2(a):
+  s1=0
+  s2=0
+  s3=0
+  for i in range(0,5):
+    if a[0][i]!=0:
+        s1=i
+        #print(f'The first film is in cluster {i+1}')
+    if a[1][i]!=0:
+       s2=i
+       #print(f'The second film is in cluster {i+1}')
+    if a[2][i]!=0:
+       s3=i
+       #print(f'The third film is in cluster {i+1}')
+  return s1, s2, s3
+
+
+
+def recom(b):
+  if b[0]==b[1]==b[2]:
+    return random.choice(cluster[b[1]])
+  if b[0]==b[1]!=b[2]:
+    return random.choice(cluster[b[1]])
+  if b[0]!=b[1]==b[2]:
+     return random.choice(cluster[b[1]])
+  if b[0]==b[2]!=b[1]:
+     return random.choice(cluster[b[2]])
+  if  b[0]!=b[2]!=b[1]:
+     return random.choice(cluster[b[0]])
+
+def original_recom(input1,input2,input3):
+  return recom(recomender2(recomender(input1,input2,input3)))
+
+a=recomender('The Ballroom','Scooby-Doo! and the Reluctant Werewolf','Last Summer')
+a
+
+b=recomender2(a)
+print(b)
+
+recom(b)
+
+cluster4.count("Trial")
+
+!pip install gradio
+
+import numpy as np
+import gradio as gr
+
+
+def original_recom(input1,input2,input3):
+  return recom(recomender2(recomender(input1,input2,input3)))
+with gr.Blocks() as demo:
+    gr.Markdown("Flip text or image files using this demo.")
+
+    input1 = gr.Textbox(placeholder='first film name...')
+
+    input2 = gr.Textbox(placeholder='second film name...')
+
+    input3 = gr.Textbox(placeholder='third film name...')
+
+    text_output=gr.Textbox( )
+
+
+    text_button = gr.Button("Submit")
+    text_button.click(original_recom, inputs=[input1,input2,input3], outputs=text_output)
+demo.launch()
+
+cluster4.count('The Sex of Angels')
+