{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import zipfile\n\nzf = zipfile.ZipFile('../input/bosch-production-line-performance/train_date.csv.zip') \ntrain_date_chunks = pd.read_csv(zf.open('train_date.csv'), iterator=True, chunksize=100000)\npd.options.display.max_columns = None\npd.options.display.max_rows = None\npd.options.display.max_colwidth = None","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_date_frame():\n for data_frame in train_date_chunks:\n yield data_frame\n \nget_df_date = get_date_frame()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_date = next(get_df_date)\n\nstation_list = []\nfirst_features_in_each_station = [] \n\ndf_date_columns = df_date.columns.tolist()\n\nfor feature in df_date_columns[1:]:\n station = feature[:feature.index('_D')]\n if station in station_list:\n continue\n else:\n station_list.append(station)\n first_features_in_each_station.append(feature)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"global_station_pairs = {}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"while True:\n temp_df = pd.DataFrame (np.array(df_date[first_features_in_each_station]), columns = station_list)\n station_list_for_each_part = temp_df.stack().reset_index(level=1).groupby(level=0, sort=False)['level_1'].apply(list)\n \n \n temp_station_df = pd.DataFrame({\"Id\": np.array(df_date[\"Id\"])})\n temp_station_df[\"Stations\"] = station_list_for_each_part\n \n try:\n station_df = station_df.append(temp_station_df, ignore_index=True)\n except:\n station_df = pd.DataFrame({\"Id\": np.array(df_date[\"Id\"])})\n station_df[\"Stations\"] = station_list_for_each_part\n \n \n for each_part in station_list_for_each_part:\n for station_cursor in range(1, len(each_part)):\n pair = (each_part[station_cursor-1], each_part[station_cursor])\n try:\n global_station_pairs[pair] += 1\n except:\n global_station_pairs[pair] = 1\n \n try:\n df_date = next(get_df_date)\n except:\n break","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"station_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"global_station_pairs = sorted(global_station_pairs.items())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"global_station_pairs","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"node_occurrences = {}\nfor line in global_station_pairs:\n pair = line[0]\n try:\n node_occurrences[pair[0]] += 1\n except:\n node_occurrences[pair[0]] = 1\n try:\n node_occurrences[pair[1]] += 1\n except:\n node_occurrences[pair[1]] = 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"node_occurrences","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"'''\nstation_df.to_csv('part_station_info.csv', index=False) \n\nwith zipfile.ZipFile('part_station_info.zip', 'w') as zipObj:\n zipObj.write(\"./part_station_info.csv\")\n print(\"part_station_info.csv file is successfuly zipped\")\n\ntry:\n os.remove(\"./part_station_info.csv\")\n print(\"part_station_info.csv file is successfuly removed\")\nexcept:\n print(\"No such file\")\n\n'''","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import networkx as nx\nimport matplotlib.pyplot as plt\n\nimport plotly.offline as py\nimport plotly.graph_objects as go","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_pair_list(station_list):\n pair_list = []\n for each in station_list:\n for station_cursor in range(1, len(each)):\n pair = (each[station_cursor-1], each[station_cursor])\n pair_list.append(pair)\n return pair_list","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def draw_station_pairs_in_a_part(pair_list, title):\n g = nx.Graph()\n for pair in pair_list:\n g.add_node(pair[0])\n g.add_node(pair[1])\n g.add_edge(pair[0], pair[1])\n \n fig = plt.figure(figsize=(10,5))\n nx.draw(g, with_labels=True)\n plt.title(title)\n plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"random_sample = station_df.sample()\nrandom_sample","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"draw_station_pairs_in_a_part(create_pair_list(random_sample['Stations']), int(random_sample['Id']))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"random_sample = station_df.sample()\nrandom_sample","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"draw_station_pairs_in_a_part(create_pair_list(random_sample['Stations']), int(random_sample['Id']))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g = nx.Graph()\nfor pair in global_station_pairs:\n stations = pair[0]\n\n g.add_node(stations[0], size = node_occurrences[stations[0]])\n g.add_node(stations[1], size = node_occurrences[stations[1]])\n g.add_edge(pair[0][0], pair[0][1], occurrence = pair[1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pos_ = nx.spring_layout(g)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def make_edge(x, y, text, width):\n return go.Scatter(x = x,\n y = y,\n line = dict(width = width,\n color = 'red'),\n hoverinfo = 'text',\n text = ([text]),\n mode = 'lines')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"edge_trace = []\nfor edge in g.edges():\n ch1 = edge[0]\n ch2 = edge[1]\n \n x0, y0 = pos_[ch1]\n x1, y1 = pos_[ch2]\n \n trace = make_edge([x0, x1, None], \n [y0, y1, None], \n text = g.edges()[edge][\"occurrence\"],\n width = 0.000005*g.edges()[edge][\"occurrence\"])\n edge_trace.append(trace)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"node_trace = go.Scatter(x = [],\n y = [],\n text = [],\n textposition = \"top center\",\n textfont_size = 10,\n mode = 'markers+text',\n hoverinfo = 'none',\n marker = dict(color = [],\n size = [],\n line = None))\n\nfor node in g.nodes():\n x, y = pos_[node]\n node_trace['x'] += tuple([x])\n node_trace['y'] += tuple([y])\n node_trace['marker']['color'] += tuple(['cornflowerblue'])\n node_trace['marker']['size'] += tuple([1*g.nodes()[node]['size']])\n node_trace['text'] += tuple(['' + node + ''])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Customize layout\nlayout = go.Layout(\n paper_bgcolor='rgba(0,0,0,0)', # transparent background\n plot_bgcolor='rgba(0,0,0,0)', # transparent 2nd background\n xaxis = {'showgrid': False, 'zeroline': False}, # no gridlines\n yaxis = {'showgrid': False, 'zeroline': False}, # no gridlines\n)\n# Create figure\nfig = go.Figure(layout = layout)\n# Add all edge traces\nfor trace in edge_trace:\n fig.add_trace(trace)\n# Add node trace\nfig.add_trace(node_trace)\n# Remove legend\nfig.update_layout(showlegend = False)\n# Remove tick labels\nfig.update_xaxes(showticklabels = False)\nfig.update_yaxes(showticklabels = False)\n# Show figure\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = plt.figure(figsize=(20,20))\nnx.draw(g, with_labels=True)\nplt.show()","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}